{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UOXQXFB2OWDHXJBYDBOL5BMJHP","short_pith_number":"pith:UOXQXFB2","canonical_record":{"source":{"id":"1707.06728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T00:50:22Z","cross_cats_sorted":[],"title_canon_sha256":"56f0e434630d7255f44eec47d76638dce806ab784b74b7086259240ff782291b","abstract_canon_sha256":"a1aa076acfe265e971443068c9ed1ed96d3261a88b209563d87da71959a1bb0f"},"schema_version":"1.0"},"canonical_sha256":"a3af0b943a75867ba438185cbe85893bec7923240d1236a48ca82fa058ca69eb","source":{"kind":"arxiv","id":"1707.06728","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06728","created_at":"2026-05-18T00:36:21Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06728v2","created_at":"2026-05-18T00:36:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06728","created_at":"2026-05-18T00:36:21Z"},{"alias_kind":"pith_short_12","alias_value":"UOXQXFB2OWDH","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UOXQXFB2OWDHXJBY","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UOXQXFB2","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UOXQXFB2OWDHXJBYDBOL5BMJHP","target":"record","payload":{"canonical_record":{"source":{"id":"1707.06728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T00:50:22Z","cross_cats_sorted":[],"title_canon_sha256":"56f0e434630d7255f44eec47d76638dce806ab784b74b7086259240ff782291b","abstract_canon_sha256":"a1aa076acfe265e971443068c9ed1ed96d3261a88b209563d87da71959a1bb0f"},"schema_version":"1.0"},"canonical_sha256":"a3af0b943a75867ba438185cbe85893bec7923240d1236a48ca82fa058ca69eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:21.870629Z","signature_b64":"Qh/VVnRXOptPWsV9bpnCgd8M7k9TCzQtqgUGbUftIh3Ra9ANIggXh7qSBKKPMizt2fsTb16ITby3zobeDFdhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3af0b943a75867ba438185cbe85893bec7923240d1236a48ca82fa058ca69eb","last_reissued_at":"2026-05-18T00:36:21.870106Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:21.870106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.06728","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ne7emYFMT2NlaqViAVSVifaxXGrohitxQta8ET0CM34//lkY7XONq1zAImno/Tet01125wsvlyTUV1qZX/rMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:01:52.251213Z"},"content_sha256":"f3777fd3a1b2c49339ac144298efd1fa426699e0b6fdc29646d9be24ad2ce5de","schema_version":"1.0","event_id":"sha256:f3777fd3a1b2c49339ac144298efd1fa426699e0b6fdc29646d9be24ad2ce5de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UOXQXFB2OWDHXJBYDBOL5BMJHP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Defenses Against Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ambrish Rawat, Maria-Irina Nicolae, Valentina Zantedeschi","submitted_at":"2017-07-21T00:50:22Z","abstract_excerpt":"Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06728","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KwWDW+c9eh4Fng3mO6FDtA37oEF+7KAQuFWsjVj5D2tOVYXaZLslbkW4jK2DdScFl6WD8ZRAcPxoxG0rJodHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:01:52.251572Z"},"content_sha256":"7994854c613f63cdff1a37a200add7a9e0e1036db2971eccf03bde19c25b6b54","schema_version":"1.0","event_id":"sha256:7994854c613f63cdff1a37a200add7a9e0e1036db2971eccf03bde19c25b6b54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOXQXFB2OWDHXJBYDBOL5BMJHP/bundle.json","state_url":"https://pith.science/pith/UOXQXFB2OWDHXJBYDBOL5BMJHP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOXQXFB2OWDHXJBYDBOL5BMJHP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T04:01:52Z","links":{"resolver":"https://pith.science/pith/UOXQXFB2OWDHXJBYDBOL5BMJHP","bundle":"https://pith.science/pith/UOXQXFB2OWDHXJBYDBOL5BMJHP/bundle.json","state":"https://pith.science/pith/UOXQXFB2OWDHXJBYDBOL5BMJHP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOXQXFB2OWDHXJBYDBOL5BMJHP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UOXQXFB2OWDHXJBYDBOL5BMJHP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a1aa076acfe265e971443068c9ed1ed96d3261a88b209563d87da71959a1bb0f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T00:50:22Z","title_canon_sha256":"56f0e434630d7255f44eec47d76638dce806ab784b74b7086259240ff782291b"},"schema_version":"1.0","source":{"id":"1707.06728","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06728","created_at":"2026-05-18T00:36:21Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06728v2","created_at":"2026-05-18T00:36:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06728","created_at":"2026-05-18T00:36:21Z"},{"alias_kind":"pith_short_12","alias_value":"UOXQXFB2OWDH","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UOXQXFB2OWDHXJBY","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UOXQXFB2","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:7994854c613f63cdff1a37a200add7a9e0e1036db2971eccf03bde19c25b6b54","target":"graph","created_at":"2026-05-18T00:36:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinfo","authors_text":"Ambrish Rawat, Maria-Irina Nicolae, Valentina Zantedeschi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T00:50:22Z","title":"Efficient Defenses Against Adversarial Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06728","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f3777fd3a1b2c49339ac144298efd1fa426699e0b6fdc29646d9be24ad2ce5de","target":"record","created_at":"2026-05-18T00:36:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a1aa076acfe265e971443068c9ed1ed96d3261a88b209563d87da71959a1bb0f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-21T00:50:22Z","title_canon_sha256":"56f0e434630d7255f44eec47d76638dce806ab784b74b7086259240ff782291b"},"schema_version":"1.0","source":{"id":"1707.06728","kind":"arxiv","version":2}},"canonical_sha256":"a3af0b943a75867ba438185cbe85893bec7923240d1236a48ca82fa058ca69eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3af0b943a75867ba438185cbe85893bec7923240d1236a48ca82fa058ca69eb","first_computed_at":"2026-05-18T00:36:21.870106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:21.870106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qh/VVnRXOptPWsV9bpnCgd8M7k9TCzQtqgUGbUftIh3Ra9ANIggXh7qSBKKPMizt2fsTb16ITby3zobeDFdhAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:21.870629Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06728","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3777fd3a1b2c49339ac144298efd1fa426699e0b6fdc29646d9be24ad2ce5de","sha256:7994854c613f63cdff1a37a200add7a9e0e1036db2971eccf03bde19c25b6b54"],"state_sha256":"a15a1194cb6d05b30211d7e23129795c20ff74c51480eadfe8664d46770e8ea5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O5dPOoN3NSdssmrEn5HgoCxXbzX/dwVJIFUVR1zVohiZcs8mdh42Uv9NNEX0E6IyebxG5umXsjmD3dabC+tHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:01:52.253486Z","bundle_sha256":"63346ff4cbca9d65ccc80c18c1bfc80cb979a22500f017bc291e99695ed135ce"}}