{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LJS4UQ7T5AB4FXT25WC4RPTZ66","short_pith_number":"pith:LJS4UQ7T","canonical_record":{"source":{"id":"1804.00499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T18:02:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9641e7deafc258f4c18d7d4f0596300520d7303cfeec70295f6e3f2d60a8fae3","abstract_canon_sha256":"d5766609f9c16ca09a526c0095c15ce428f8739c327194e7013419a640fec426"},"schema_version":"1.0"},"canonical_sha256":"5a65ca43f3e803c2de7aed85c8be79f791afaae07b9051dc0959a4014918e0f1","source":{"kind":"arxiv","id":"1804.00499","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00499","created_at":"2026-05-18T00:19:36Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00499v1","created_at":"2026-05-18T00:19:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00499","created_at":"2026-05-18T00:19:36Z"},{"alias_kind":"pith_short_12","alias_value":"LJS4UQ7T5AB4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LJS4UQ7T5AB4FXT2","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LJS4UQ7T","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LJS4UQ7T5AB4FXT25WC4RPTZ66","target":"record","payload":{"canonical_record":{"source":{"id":"1804.00499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T18:02:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9641e7deafc258f4c18d7d4f0596300520d7303cfeec70295f6e3f2d60a8fae3","abstract_canon_sha256":"d5766609f9c16ca09a526c0095c15ce428f8739c327194e7013419a640fec426"},"schema_version":"1.0"},"canonical_sha256":"5a65ca43f3e803c2de7aed85c8be79f791afaae07b9051dc0959a4014918e0f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:36.985149Z","signature_b64":"8VYY5ug9GFvYsm1klXYQrc9qjebxdGVt6gkLE8Xruz9V+ZZbyEuCFoKvTqlkzeQEhSWt9XzK1QNilo7hTGEAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a65ca43f3e803c2de7aed85c8be79f791afaae07b9051dc0959a4014918e0f1","last_reissued_at":"2026-05-18T00:19:36.984488Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:36.984488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.00499","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4ttpT/uhfFf+l1DSOysTwXZmAY24ahY8/nKZDTzTp+3UDZ+oZNyR3zfUrrXRdM/jLPrOyVyRJDPAqmIJk2tBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:50:56.175604Z"},"content_sha256":"26bc48e410f7805f8f5e63487b49dc87e23d450ac33eeea567f776a98076d974","schema_version":"1.0","event_id":"sha256:26bc48e410f7805f8f5e63487b49dc87e23d450ac33eeea567f776a98076d974"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LJS4UQ7T5AB4FXT25WC4RPTZ66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hossein Hosseini, Radha Poovendran","submitted_at":"2018-03-16T18:02:14Z","abstract_excerpt":"Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the model prediction error. Such images, however, contain artificial perturbations that make them somewhat distinguishable from natural images. This property is used by several defense methods to counter adversarial examples by applying denoising filters or training the model to be robust to small perturbations.\n  In this paper, we introduce a new class of adve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00499","kind":"arxiv","version":1},"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":"2026-05-18T00:19:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UHPeMoxW8VzyYirBaLfIGWK77Lhwy77aIMJvJ6hQ/ACibfNOQSzqAzzRPPE54OXHBXI3RS4WwYeX8F5bKheFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:50:56.175958Z"},"content_sha256":"dd52f99baac00510938067e620a6e4d151975a558aff7b6da16f60f363d1934a","schema_version":"1.0","event_id":"sha256:dd52f99baac00510938067e620a6e4d151975a558aff7b6da16f60f363d1934a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJS4UQ7T5AB4FXT25WC4RPTZ66/bundle.json","state_url":"https://pith.science/pith/LJS4UQ7T5AB4FXT25WC4RPTZ66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJS4UQ7T5AB4FXT25WC4RPTZ66/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":"2026-05-30T09:50:56Z","links":{"resolver":"https://pith.science/pith/LJS4UQ7T5AB4FXT25WC4RPTZ66","bundle":"https://pith.science/pith/LJS4UQ7T5AB4FXT25WC4RPTZ66/bundle.json","state":"https://pith.science/pith/LJS4UQ7T5AB4FXT25WC4RPTZ66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJS4UQ7T5AB4FXT25WC4RPTZ66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LJS4UQ7T5AB4FXT25WC4RPTZ66","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":"d5766609f9c16ca09a526c0095c15ce428f8739c327194e7013419a640fec426","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T18:02:14Z","title_canon_sha256":"9641e7deafc258f4c18d7d4f0596300520d7303cfeec70295f6e3f2d60a8fae3"},"schema_version":"1.0","source":{"id":"1804.00499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00499","created_at":"2026-05-18T00:19:36Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00499v1","created_at":"2026-05-18T00:19:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00499","created_at":"2026-05-18T00:19:36Z"},{"alias_kind":"pith_short_12","alias_value":"LJS4UQ7T5AB4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LJS4UQ7T5AB4FXT2","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LJS4UQ7T","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:dd52f99baac00510938067e620a6e4d151975a558aff7b6da16f60f363d1934a","target":"graph","created_at":"2026-05-18T00:19:36Z","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":"Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the model prediction error. Such images, however, contain artificial perturbations that make them somewhat distinguishable from natural images. This property is used by several defense methods to counter adversarial examples by applying denoising filters or training the model to be robust to small perturbations.\n  In this paper, we introduce a new class of adve","authors_text":"Hossein Hosseini, Radha Poovendran","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T18:02:14Z","title":"Semantic Adversarial Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00499","kind":"arxiv","version":1},"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":"sha256:26bc48e410f7805f8f5e63487b49dc87e23d450ac33eeea567f776a98076d974","target":"record","created_at":"2026-05-18T00:19:36Z","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":"d5766609f9c16ca09a526c0095c15ce428f8739c327194e7013419a640fec426","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-16T18:02:14Z","title_canon_sha256":"9641e7deafc258f4c18d7d4f0596300520d7303cfeec70295f6e3f2d60a8fae3"},"schema_version":"1.0","source":{"id":"1804.00499","kind":"arxiv","version":1}},"canonical_sha256":"5a65ca43f3e803c2de7aed85c8be79f791afaae07b9051dc0959a4014918e0f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a65ca43f3e803c2de7aed85c8be79f791afaae07b9051dc0959a4014918e0f1","first_computed_at":"2026-05-18T00:19:36.984488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:36.984488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8VYY5ug9GFvYsm1klXYQrc9qjebxdGVt6gkLE8Xruz9V+ZZbyEuCFoKvTqlkzeQEhSWt9XzK1QNilo7hTGEAAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:36.985149Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.00499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26bc48e410f7805f8f5e63487b49dc87e23d450ac33eeea567f776a98076d974","sha256:dd52f99baac00510938067e620a6e4d151975a558aff7b6da16f60f363d1934a"],"state_sha256":"a3d74ac4962d47c368804b824d5cc2fb939069e7f65da4168a24f365d4cb7b2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6fMd2vSjg98Br3lJOB/7otzijNosgNhzqBHBlPw4aNToE+YtWWK3WSyb6okFzFZpxlEL1V/pdSZS/2pHdR2rAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:50:56.178043Z","bundle_sha256":"638f6e6d94708db691a0e001431ec68346f63a7685ccc6b4ef1d4bad064c30da"}}