A small tool to view real-world ActivityPub objects as JSON! Enter a URL
or username from Mastodon or a similar service below, and we'll send a
request with
the right
Accept
header
to the server to view the underlying object.
{
"@context": [
"https://www.w3.org/ns/activitystreams",
{
"ostatus": "http://ostatus.org#",
"atomUri": "ostatus:atomUri",
"inReplyToAtomUri": "ostatus:inReplyToAtomUri",
"conversation": "ostatus:conversation",
"sensitive": "as:sensitive",
"toot": "http://joinmastodon.org/ns#",
"votersCount": "toot:votersCount",
"litepub": "http://litepub.social/ns#",
"directMessage": "litepub:directMessage",
"blurhash": "toot:blurhash",
"focalPoint": {
"@container": "@list",
"@id": "toot:focalPoint"
}
}
],
"id": "https://infosec.exchange/users/b4rbito/outbox?page=true",
"type": "OrderedCollectionPage",
"prev": "https://infosec.exchange/users/b4rbito/outbox?min_id=112992734842066038&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/outbox",
"orderedItems": [
{
"id": "https://infosec.exchange/users/b4rbito/statuses/112992734842066038/activity",
"type": "Announce",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2024-08-20T05:38:26Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://haunted.computer/users/phrack",
"https://infosec.exchange/users/b4rbito/followers"
],
"object": "https://haunted.computer/users/phrack/statuses/112990587684381825"
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/111860874404831148/activity",
"type": "Announce",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2024-02-02T08:11:26Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://haunted.computer/users/netspooky",
"https://infosec.exchange/users/b4rbito/followers"
],
"object": "https://haunted.computer/users/netspooky/statuses/111858309779648089"
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/111378905848817983/activity",
"type": "Announce",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-11-09T05:20:30Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://mastodon.social/users/airspeedswift",
"https://infosec.exchange/users/b4rbito/followers"
],
"object": "https://mastodon.social/users/airspeedswift/statuses/111308376179609498"
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/111345677025454357/activity",
"type": "Announce",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-11-03T08:29:58Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://mastodon.social/users/fj",
"https://infosec.exchange/users/b4rbito/followers"
],
"object": "https://mastodon.social/users/fj/statuses/111311393349826157"
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/111341779419468173/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-11-02T15:58:46Z",
"to": [
"https://infosec.exchange/users/b4rbito/followers"
],
"cc": [
"https://www.w3.org/ns/activitystreams#Public",
"https://uwu.social/users/koakuma"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/111341779419468173",
"type": "Note",
"summary": null,
"inReplyTo": "https://uwu.social/users/koakuma/statuses/111341681301024739",
"published": "2023-11-02T15:58:46Z",
"url": "https://infosec.exchange/@b4rbito/111341779419468173",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://infosec.exchange/users/b4rbito/followers"
],
"cc": [
"https://www.w3.org/ns/activitystreams#Public",
"https://uwu.social/users/koakuma"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/111341779419468173",
"inReplyToAtomUri": "https://uwu.social/users/koakuma/statuses/111341681301024739",
"conversation": "tag:infosec.exchange,2023-11-02:objectId=107274095:objectType=Conversation",
"content": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://uwu.social/@koakuma\" class=\"u-url mention\">@<span>koakuma</span></a></span> unfortunately we haven't tested, but I'm pretty confident that on Intel, even on less powerful CPUs the results should be the same. I expect same results for the same microarchitectural generation.</p><p>While for ARM we can't say: with Apple M1 we observed less performance benefits, but still I do believe there is potential there.</p>",
"contentMap": {
"en": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://uwu.social/@koakuma\" class=\"u-url mention\">@<span>koakuma</span></a></span> unfortunately we haven't tested, but I'm pretty confident that on Intel, even on less powerful CPUs the results should be the same. I expect same results for the same microarchitectural generation.</p><p>While for ARM we can't say: with Apple M1 we observed less performance benefits, but still I do believe there is potential there.</p>"
},
"attachment": [],
"tag": [
{
"type": "Mention",
"href": "https://uwu.social/users/koakuma",
"name": "@koakuma@uwu.social"
}
],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/111341779419468173/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/111341779419468173/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/111341779419468173/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/111341779419468173/likes",
"type": "Collection",
"totalItems": 1
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/111341779419468173/shares",
"type": "Collection",
"totalItems": 0
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/111339979920774803/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-11-02T08:21:07Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/111339979920774803",
"type": "Note",
"summary": null,
"inReplyTo": null,
"published": "2023-11-02T08:21:07Z",
"url": "https://infosec.exchange/@b4rbito/111339979920774803",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/111339979920774803",
"inReplyToAtomUri": null,
"conversation": "tag:infosec.exchange,2023-11-02:objectId=107274095:objectType=Conversation",
"content": "<p>Have a look at our new ;login article: <a href=\"https://www.usenix.org/publications/loginonline/floatzone-how-floating-point-additions-can-detect-memory-errors\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://www.</span><span class=\"ellipsis\">usenix.org/publications/logino</span><span class=\"invisible\">nline/floatzone-how-floating-point-additions-can-detect-memory-errors</span></a></p>",
"contentMap": {
"en": "<p>Have a look at our new ;login article: <a href=\"https://www.usenix.org/publications/loginonline/floatzone-how-floating-point-additions-can-detect-memory-errors\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://www.</span><span class=\"ellipsis\">usenix.org/publications/logino</span><span class=\"invisible\">nline/floatzone-how-floating-point-additions-can-detect-memory-errors</span></a></p>"
},
"attachment": [
{
"type": "Document",
"mediaType": "image/png",
"url": "https://media.infosec.exchange/infosec.exchange/media_attachments/files/111/339/979/785/775/202/original/588f257ad40725c7.png",
"name": null,
"blurhash": "UaQvtPjtXCaz4WjtNNa}9IjtR;j]02ayR.ay",
"width": 1341,
"height": 628
}
],
"tag": [],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/111339979920774803/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/111339979920774803/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/111339979920774803/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/111339979920774803/likes",
"type": "Collection",
"totalItems": 12
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/111339979920774803/shares",
"type": "Collection",
"totalItems": 9
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/111277134703261093/activity",
"type": "Announce",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-10-22T05:58:45Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/gannimo",
"https://infosec.exchange/users/b4rbito/followers"
],
"object": "https://infosec.exchange/users/gannimo/statuses/111272500276982164"
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110915336494862511/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-08-19T08:28:43Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110915336494862511",
"type": "Note",
"summary": null,
"inReplyTo": null,
"published": "2023-08-19T08:28:43Z",
"url": "https://infosec.exchange/@b4rbito/110915336494862511",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/110915336494862511",
"inReplyToAtomUri": null,
"conversation": "tag:infosec.exchange,2023-08-19:objectId=88382288:objectType=Conversation",
"content": "<p>Cool, apparently Google is going to release a new blog post on RIDL/MDS:</p><p>"Add X25519 MDS exploits for blog post."</p><p><a href=\"https://github.com/google/security-research/tree/master/pocs/cpus/mds-x25519\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">github.com/google/security-res</span><span class=\"invisible\">earch/tree/master/pocs/cpus/mds-x25519</span></a></p>",
"contentMap": {
"en": "<p>Cool, apparently Google is going to release a new blog post on RIDL/MDS:</p><p>"Add X25519 MDS exploits for blog post."</p><p><a href=\"https://github.com/google/security-research/tree/master/pocs/cpus/mds-x25519\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">github.com/google/security-res</span><span class=\"invisible\">earch/tree/master/pocs/cpus/mds-x25519</span></a></p>"
},
"attachment": [],
"tag": [],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110915336494862511/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/110915336494862511/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/110915336494862511/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110915336494862511/likes",
"type": "Collection",
"totalItems": 2
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110915336494862511/shares",
"type": "Collection",
"totalItems": 0
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110855219285661283/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-08-08T17:40:07Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110855219285661283",
"type": "Note",
"summary": null,
"inReplyTo": null,
"published": "2023-08-08T17:40:07Z",
"url": "https://infosec.exchange/@b4rbito/110855219285661283",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/110855219285661283",
"inReplyToAtomUri": null,
"conversation": "tag:infosec.exchange,2023-08-08:objectId=85653142:objectType=Conversation",
"content": "<p>Busy day for microarchitectural attacks 😍</p><p><a href=\"https://comsec.ethz.ch/research/microarch/inception/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">comsec.ethz.ch/research/microa</span><span class=\"invisible\">rch/inception/</span></a></p><p><a href=\"https://downfall.page/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"\">downfall.page/</span><span class=\"invisible\"></span></a></p>",
"contentMap": {
"en": "<p>Busy day for microarchitectural attacks 😍</p><p><a href=\"https://comsec.ethz.ch/research/microarch/inception/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">comsec.ethz.ch/research/microa</span><span class=\"invisible\">rch/inception/</span></a></p><p><a href=\"https://downfall.page/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"\">downfall.page/</span><span class=\"invisible\"></span></a></p>"
},
"attachment": [],
"tag": [],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110855219285661283/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/110855219285661283/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/110855219285661283/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110855219285661283/likes",
"type": "Collection",
"totalItems": 20
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110855219285661283/shares",
"type": "Collection",
"totalItems": 16
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110694277838042241/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-07-11T07:30:35Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://infosec.exchange/users/madcoder",
"https://mastodon.online/users/ezhes_"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694277838042241",
"type": "Note",
"summary": null,
"inReplyTo": "https://infosec.exchange/users/madcoder/statuses/110694254670511564",
"published": "2023-07-11T07:30:35Z",
"url": "https://infosec.exchange/@b4rbito/110694277838042241",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://infosec.exchange/users/madcoder",
"https://mastodon.online/users/ezhes_"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/110694277838042241",
"inReplyToAtomUri": "https://infosec.exchange/users/madcoder/statuses/110694254670511564",
"conversation": "tag:mastodon.online,2023-07-11:objectId=190068566:objectType=Conversation",
"content": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://infosec.exchange/@madcoder\" class=\"u-url mention\">@<span>madcoder</span></a></span> <span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> I'm 99% sure we run this with exceptions disabled. Let me verify this<br />Yes confirmed: exceptions disabled. We were really curious about the overhead of the instruction itself</p>",
"contentMap": {
"en": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://infosec.exchange/@madcoder\" class=\"u-url mention\">@<span>madcoder</span></a></span> <span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> I'm 99% sure we run this with exceptions disabled. Let me verify this<br />Yes confirmed: exceptions disabled. We were really curious about the overhead of the instruction itself</p>"
},
"updated": "2023-07-11T07:33:56Z",
"attachment": [],
"tag": [
{
"type": "Mention",
"href": "https://infosec.exchange/users/madcoder",
"name": "@madcoder"
},
{
"type": "Mention",
"href": "https://mastodon.online/users/ezhes_",
"name": "@ezhes_@mastodon.online"
}
],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694277838042241/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/110694277838042241/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/110694277838042241/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694277838042241/likes",
"type": "Collection",
"totalItems": 1
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694277838042241/shares",
"type": "Collection",
"totalItems": 0
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110694274637251370/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-07-11T07:29:47Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://infosec.exchange/users/madcoder",
"https://mastodon.online/users/ezhes_"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694274637251370",
"type": "Note",
"summary": null,
"inReplyTo": "https://infosec.exchange/users/madcoder/statuses/110694242747747574",
"published": "2023-07-11T07:29:47Z",
"url": "https://infosec.exchange/@b4rbito/110694274637251370",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://infosec.exchange/users/madcoder",
"https://mastodon.online/users/ezhes_"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/110694274637251370",
"inReplyToAtomUri": "https://infosec.exchange/users/madcoder/statuses/110694242747747574",
"conversation": "tag:mastodon.online,2023-07-11:objectId=190068566:objectType=Conversation",
"content": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://infosec.exchange/@madcoder\" class=\"u-url mention\">@<span>madcoder</span></a></span> <span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> native arm</p>",
"contentMap": {
"en": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://infosec.exchange/@madcoder\" class=\"u-url mention\">@<span>madcoder</span></a></span> <span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> native arm</p>"
},
"attachment": [],
"tag": [
{
"type": "Mention",
"href": "https://infosec.exchange/users/madcoder",
"name": "@madcoder"
},
{
"type": "Mention",
"href": "https://mastodon.online/users/ezhes_",
"name": "@ezhes_@mastodon.online"
}
],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694274637251370/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/110694274637251370/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/110694274637251370/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694274637251370/likes",
"type": "Collection",
"totalItems": 0
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694274637251370/shares",
"type": "Collection",
"totalItems": 0
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110694230112267109/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-07-11T07:18:27Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://infosec.exchange/users/madcoder",
"https://mastodon.online/users/ezhes_"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694230112267109",
"type": "Note",
"summary": null,
"inReplyTo": "https://infosec.exchange/users/madcoder/statuses/110693908284239947",
"published": "2023-07-11T07:18:27Z",
"url": "https://infosec.exchange/@b4rbito/110694230112267109",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://infosec.exchange/users/madcoder",
"https://mastodon.online/users/ezhes_"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/110694230112267109",
"inReplyToAtomUri": "https://infosec.exchange/users/madcoder/statuses/110693908284239947",
"conversation": "tag:mastodon.online,2023-07-11:objectId=190068566:objectType=Conversation",
"content": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://infosec.exchange/@madcoder\" class=\"u-url mention\">@<span>madcoder</span></a></span> <span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> <br />This is absolutely true, however in this benchmark we only add vaddss or cmp+je after every load/store. (No RedZone or libc instrumentation)<br />The overhead is still quite significant.</p>",
"contentMap": {
"en": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://infosec.exchange/@madcoder\" class=\"u-url mention\">@<span>madcoder</span></a></span> <span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> <br />This is absolutely true, however in this benchmark we only add vaddss or cmp+je after every load/store. (No RedZone or libc instrumentation)<br />The overhead is still quite significant.</p>"
},
"attachment": [
{
"type": "Document",
"mediaType": "image/jpeg",
"url": "https://media.infosec.exchange/infosec.exchange/media_attachments/files/110/694/226/855/301/272/original/8870859af63705f8.jpg",
"name": null,
"blurhash": "UKRfkAWr?bkDbwj[adWV_4WAIUoLr;ofkXay",
"width": 1080,
"height": 710
}
],
"tag": [
{
"type": "Mention",
"href": "https://infosec.exchange/users/madcoder",
"name": "@madcoder"
},
{
"type": "Mention",
"href": "https://mastodon.online/users/ezhes_",
"name": "@ezhes_@mastodon.online"
}
],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694230112267109/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/110694230112267109/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/110694230112267109/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694230112267109/likes",
"type": "Collection",
"totalItems": 0
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694230112267109/shares",
"type": "Collection",
"totalItems": 0
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110694166363950571/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-07-11T07:02:14Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://mastodon.online/users/ezhes_",
"https://infosec.exchange/users/vusec"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694166363950571",
"type": "Note",
"summary": null,
"inReplyTo": "https://mastodon.online/users/ezhes_/statuses/110693965685465641",
"published": "2023-07-11T07:02:14Z",
"url": "https://infosec.exchange/@b4rbito/110694166363950571",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://mastodon.online/users/ezhes_",
"https://infosec.exchange/users/vusec"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/110694166363950571",
"inReplyToAtomUri": "https://mastodon.online/users/ezhes_/statuses/110693965685465641",
"conversation": "tag:mastodon.online,2023-07-11:objectId=190068566:objectType=Conversation",
"content": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> <span class=\"h-card\" translate=\"no\"><a href=\"https://infosec.exchange/@vusec\" class=\"u-url mention\">@<span>vusec</span></a></span> Ok now I understood.</p><p>We tried to get detailed root causes of float checks overhead but it's really complex. I'll give here some examples:</p><p>[1] Using ubench to compare</p><p>vaddss xmm0, xmm0, [rdi]</p><p>vs</p><p>cmp word ptr [rdi], 0x8b8b8b8b<br />Je 1f<br />1:</p><p>We get the results in the attached figure (left vaddss, right cmp).<br />Cmp+je should be faster (look at clock cycles) however when applied to SPEC benchmarks vaddss is much faster. I guess it is mostly due to the fact that vaddss is very friendly on piepeline scheduling: they can be executed out of order and the result is never used by subsequent instructions avoiding dependency issues.</p><p>[2] Our current instrumentation of mem* family is not ideal. We first loop over all the memory to check for RedZone values, and only after we perform the mem* operation. This is really bad from the cache/memory side. Ideally we should interleave the two but it's not easy.</p><p>[3] By adding an equivalent amount of "nops" instead of the checks we still get a measurable slow down and an increase of 1.5% in Branch misprediction. So code alignment and intrusive addition of instructions can affect heavily the overhead </p><p>In conclusion we decided to base our claims on SPEC benchmarks. All the above experiments show how the overhead is really affected by a lot of conditions. I do believe that any micro benchmark will hide some source of overheads.<br />On the other hand with this approach it is really hard to determine the root cause</p>",
"contentMap": {
"en": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> <span class=\"h-card\" translate=\"no\"><a href=\"https://infosec.exchange/@vusec\" class=\"u-url mention\">@<span>vusec</span></a></span> Ok now I understood.</p><p>We tried to get detailed root causes of float checks overhead but it's really complex. I'll give here some examples:</p><p>[1] Using ubench to compare</p><p>vaddss xmm0, xmm0, [rdi]</p><p>vs</p><p>cmp word ptr [rdi], 0x8b8b8b8b<br />Je 1f<br />1:</p><p>We get the results in the attached figure (left vaddss, right cmp).<br />Cmp+je should be faster (look at clock cycles) however when applied to SPEC benchmarks vaddss is much faster. I guess it is mostly due to the fact that vaddss is very friendly on piepeline scheduling: they can be executed out of order and the result is never used by subsequent instructions avoiding dependency issues.</p><p>[2] Our current instrumentation of mem* family is not ideal. We first loop over all the memory to check for RedZone values, and only after we perform the mem* operation. This is really bad from the cache/memory side. Ideally we should interleave the two but it's not easy.</p><p>[3] By adding an equivalent amount of "nops" instead of the checks we still get a measurable slow down and an increase of 1.5% in Branch misprediction. So code alignment and intrusive addition of instructions can affect heavily the overhead </p><p>In conclusion we decided to base our claims on SPEC benchmarks. All the above experiments show how the overhead is really affected by a lot of conditions. I do believe that any micro benchmark will hide some source of overheads.<br />On the other hand with this approach it is really hard to determine the root cause</p>"
},
"updated": "2023-07-11T07:13:55Z",
"attachment": [
{
"type": "Document",
"mediaType": "image/png",
"url": "https://media.infosec.exchange/infosec.exchange/media_attachments/files/110/694/127/530/870/177/original/072a1c4af31940cf.png",
"name": null,
"blurhash": "UiOyxLR%ofNE8yoeayt6%fjuj@oLWAayfQae",
"width": 1897,
"height": 761
}
],
"tag": [
{
"type": "Mention",
"href": "https://mastodon.online/users/ezhes_",
"name": "@ezhes_@mastodon.online"
},
{
"type": "Mention",
"href": "https://infosec.exchange/users/vusec",
"name": "@vusec"
}
],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694166363950571/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/110694166363950571/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/110694166363950571/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694166363950571/likes",
"type": "Collection",
"totalItems": 0
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110694166363950571/shares",
"type": "Collection",
"totalItems": 0
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110693866967389366/activity",
"type": "Announce",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-07-11T05:46:06Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://mastodon.online/users/ezhes_",
"https://infosec.exchange/users/b4rbito/followers"
],
"object": "https://mastodon.online/users/ezhes_/statuses/110693219902942418"
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110693854034777171/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-07-11T05:42:49Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://mastodon.online/users/ezhes_"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110693854034777171",
"type": "Note",
"summary": null,
"inReplyTo": "https://mastodon.online/users/ezhes_/statuses/110693242337542411",
"published": "2023-07-11T05:42:49Z",
"url": "https://infosec.exchange/@b4rbito/110693854034777171",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers",
"https://mastodon.online/users/ezhes_"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/110693854034777171",
"inReplyToAtomUri": "https://mastodon.online/users/ezhes_/statuses/110693242337542411",
"conversation": "tag:mastodon.online,2023-07-11:objectId=190068566:objectType=Conversation",
"content": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> Ehy! One of the author here. If you look we tried to find an explanation in figure 7 of the paper. Section 7.3 also contain our analysis on this.</p><p>We tried some ubenchmark but it's really hard to come up with a clear overhead source. For sure we are keeping more busy execution ports that may slow down other instruction issue </p><p>Really glad you enjoyed the work ♥️</p>",
"contentMap": {
"en": "<p><span class=\"h-card\" translate=\"no\"><a href=\"https://mastodon.online/@ezhes_\" class=\"u-url mention\">@<span>ezhes_</span></a></span> Ehy! One of the author here. If you look we tried to find an explanation in figure 7 of the paper. Section 7.3 also contain our analysis on this.</p><p>We tried some ubenchmark but it's really hard to come up with a clear overhead source. For sure we are keeping more busy execution ports that may slow down other instruction issue </p><p>Really glad you enjoyed the work ♥️</p>"
},
"updated": "2023-07-11T05:45:24Z",
"attachment": [],
"tag": [
{
"type": "Mention",
"href": "https://mastodon.online/users/ezhes_",
"name": "@ezhes_@mastodon.online"
}
],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110693854034777171/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/110693854034777171/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/110693854034777171/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110693854034777171/likes",
"type": "Collection",
"totalItems": 4
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110693854034777171/shares",
"type": "Collection",
"totalItems": 0
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110691058589443143/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-07-10T17:51:54Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110691058589443143",
"type": "Note",
"summary": null,
"inReplyTo": null,
"published": "2023-07-10T17:51:54Z",
"url": "https://infosec.exchange/@b4rbito/110691058589443143",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/110691058589443143",
"inReplyToAtomUri": null,
"conversation": "tag:infosec.exchange,2023-07-10:objectId=77724893:objectType=Conversation",
"content": "<p>Floating Point Unit goes brrr 💨</p><p>Have a look at our latest work where we demonstrate how FP additions can be faster than standard branch instructions. </p><p>We built a full sanitizer out of this trick that incurs in only a 37% slowdown!</p><p>More information here: <a href=\"https://www.vusec.net/projects/floatzone/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://www.</span><span class=\"\">vusec.net/projects/floatzone/</span><span class=\"invisible\"></span></a></p>",
"contentMap": {
"en": "<p>Floating Point Unit goes brrr 💨</p><p>Have a look at our latest work where we demonstrate how FP additions can be faster than standard branch instructions. </p><p>We built a full sanitizer out of this trick that incurs in only a 37% slowdown!</p><p>More information here: <a href=\"https://www.vusec.net/projects/floatzone/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://www.</span><span class=\"\">vusec.net/projects/floatzone/</span><span class=\"invisible\"></span></a></p>"
},
"attachment": [
{
"type": "Document",
"mediaType": "image/jpeg",
"url": "https://media.infosec.exchange/infosec.exchange/media_attachments/files/110/691/056/124/438/764/original/8b30eb6713a5f217.jpg",
"name": null,
"blurhash": "U9SFw=?^Zh=|ozkqyDV@?^tRWVo}.9L~IAS2",
"width": 1079,
"height": 573
}
],
"tag": [],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110691058589443143/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/110691058589443143/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/110691058589443143/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110691058589443143/likes",
"type": "Collection",
"totalItems": 4
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/110691058589443143/shares",
"type": "Collection",
"totalItems": 1
}
}
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/110566226401473520/activity",
"type": "Announce",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-06-18T16:45:26Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/TumpiConIT",
"https://infosec.exchange/users/b4rbito/followers"
],
"object": "https://infosec.exchange/users/TumpiConIT/statuses/110565084753557425"
},
{
"id": "https://infosec.exchange/users/b4rbito/statuses/109716750035182673/activity",
"type": "Create",
"actor": "https://infosec.exchange/users/b4rbito",
"published": "2023-01-19T16:12:25Z",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"object": {
"id": "https://infosec.exchange/users/b4rbito/statuses/109716750035182673",
"type": "Note",
"summary": null,
"inReplyTo": null,
"published": "2023-01-19T16:12:25Z",
"url": "https://infosec.exchange/@b4rbito/109716750035182673",
"attributedTo": "https://infosec.exchange/users/b4rbito",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://infosec.exchange/users/b4rbito/followers"
],
"sensitive": false,
"atomUri": "https://infosec.exchange/users/b4rbito/statuses/109716750035182673",
"inReplyToAtomUri": null,
"conversation": "tag:infosec.exchange,2023-01-19:objectId=38520495:objectType=Conversation",
"content": "<p>I made a small repo to reproduce ZDI on your system if you are interested. <a href=\"https://github.com/enbarberis/zero_dividend_injection\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">github.com/enbarberis/zero_div</span><span class=\"invisible\">idend_injection</span></a></p><p>Very fascinating paper!<br /><a href=\"https://arxiv.org/pdf/2301.07642.pdf\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"\">arxiv.org/pdf/2301.07642.pdf</span><span class=\"invisible\"></span></a></p>",
"contentMap": {
"en": "<p>I made a small repo to reproduce ZDI on your system if you are interested. <a href=\"https://github.com/enbarberis/zero_dividend_injection\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">github.com/enbarberis/zero_div</span><span class=\"invisible\">idend_injection</span></a></p><p>Very fascinating paper!<br /><a href=\"https://arxiv.org/pdf/2301.07642.pdf\" target=\"_blank\" rel=\"nofollow noopener noreferrer\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"\">arxiv.org/pdf/2301.07642.pdf</span><span class=\"invisible\"></span></a></p>"
},
"attachment": [],
"tag": [],
"replies": {
"id": "https://infosec.exchange/users/b4rbito/statuses/109716750035182673/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://infosec.exchange/users/b4rbito/statuses/109716750035182673/replies?only_other_accounts=true&page=true",
"partOf": "https://infosec.exchange/users/b4rbito/statuses/109716750035182673/replies",
"items": []
}
},
"likes": {
"id": "https://infosec.exchange/users/b4rbito/statuses/109716750035182673/likes",
"type": "Collection",
"totalItems": 0
},
"shares": {
"id": "https://infosec.exchange/users/b4rbito/statuses/109716750035182673/shares",
"type": "Collection",
"totalItems": 0
}
}
}
]
}