{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2TX4EDQHUI5DWMBJQP2GCJJH5I","short_pith_number":"pith:2TX4EDQH","canonical_record":{"source":{"id":"1704.01155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-04T18:56:53Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"3f5f9aee0e3d8e3c374e8656b95f176230db156fe43a904a24ad554645c8c41b","abstract_canon_sha256":"b029e7b852bd4077b54c44d7e0e27de230689dfc97e72b4d23b60ff512d1cd2d"},"schema_version":"1.0"},"canonical_sha256":"d4efc20e07a23a3b302983f4612527ea1a482ec87a49926136f96abe259a3bcc","source":{"kind":"arxiv","id":"1704.01155","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01155","created_at":"2026-05-18T00:28:40Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01155v2","created_at":"2026-05-18T00:28:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01155","created_at":"2026-05-18T00:28:40Z"},{"alias_kind":"pith_short_12","alias_value":"2TX4EDQHUI5D","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2TX4EDQHUI5DWMBJ","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2TX4EDQH","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2TX4EDQHUI5DWMBJQP2GCJJH5I","target":"record","payload":{"canonical_record":{"source":{"id":"1704.01155","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-04T18:56:53Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"3f5f9aee0e3d8e3c374e8656b95f176230db156fe43a904a24ad554645c8c41b","abstract_canon_sha256":"b029e7b852bd4077b54c44d7e0e27de230689dfc97e72b4d23b60ff512d1cd2d"},"schema_version":"1.0"},"canonical_sha256":"d4efc20e07a23a3b302983f4612527ea1a482ec87a49926136f96abe259a3bcc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:40.958213Z","signature_b64":"T7IqX2QlAYnpckHNvLfsi/ixzd/nRjypwPg1MSEFN5sDpweAJaarNHzNc57znOlyvBPolE+3eFfcDV93sE0HBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4efc20e07a23a3b302983f4612527ea1a482ec87a49926136f96abe259a3bcc","last_reissued_at":"2026-05-18T00:28:40.957495Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:40.957495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.01155","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":"2026-05-18T00:28:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"smXX81gIRwgveyj5T1AR9CWAscYTpHGzAJKthuxgoIL0ugStwcP+6U+q1Yt/gKbymHRGnfRwQ4jarCsDJmn6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T08:13:05.084808Z"},"content_sha256":"9392c3917262248d5e72f57786fbbbbd535aa3327881bbfcdb76d61b3fd38707","schema_version":"1.0","event_id":"sha256:9392c3917262248d5e72f57786fbbbbd535aa3327881bbfcdb76d61b3fd38707"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2TX4EDQHUI5DWMBJQP2GCJJH5I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"David Evans, Weilin Xu, Yanjun Qi","submitted_at":"2017-04-04T18:56:53Z","abstract_excerpt":"Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \\emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, \\emph{feature squeezing}, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01155","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":"2026-05-18T00:28:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jjvWH6ThGx1Sz3qoBGZ1rACctW7fHIsfauPaDGf+Tw0jrPk0NxDjOuq4JKdpjWhUyyGKsRpSMOjpz1htieKdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T08:13:05.085189Z"},"content_sha256":"cc5494c3a47093ba34eb9d966b34fab08e1ed7b688832cb65021cc5d8d3e9135","schema_version":"1.0","event_id":"sha256:cc5494c3a47093ba34eb9d966b34fab08e1ed7b688832cb65021cc5d8d3e9135"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TX4EDQHUI5DWMBJQP2GCJJH5I/bundle.json","state_url":"https://pith.science/pith/2TX4EDQHUI5DWMBJQP2GCJJH5I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TX4EDQHUI5DWMBJQP2GCJJH5I/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":"2026-06-12T08:13:05Z","links":{"resolver":"https://pith.science/pith/2TX4EDQHUI5DWMBJQP2GCJJH5I","bundle":"https://pith.science/pith/2TX4EDQHUI5DWMBJQP2GCJJH5I/bundle.json","state":"https://pith.science/pith/2TX4EDQHUI5DWMBJQP2GCJJH5I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TX4EDQHUI5DWMBJQP2GCJJH5I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2TX4EDQHUI5DWMBJQP2GCJJH5I","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":"b029e7b852bd4077b54c44d7e0e27de230689dfc97e72b4d23b60ff512d1cd2d","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-04T18:56:53Z","title_canon_sha256":"3f5f9aee0e3d8e3c374e8656b95f176230db156fe43a904a24ad554645c8c41b"},"schema_version":"1.0","source":{"id":"1704.01155","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01155","created_at":"2026-05-18T00:28:40Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01155v2","created_at":"2026-05-18T00:28:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01155","created_at":"2026-05-18T00:28:40Z"},{"alias_kind":"pith_short_12","alias_value":"2TX4EDQHUI5D","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2TX4EDQHUI5DWMBJ","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2TX4EDQH","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:cc5494c3a47093ba34eb9d966b34fab08e1ed7b688832cb65021cc5d8d3e9135","target":"graph","created_at":"2026-05-18T00:28:40Z","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":"Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \\emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, \\emph{feature squeezing}, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing ","authors_text":"David Evans, Weilin Xu, Yanjun Qi","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-04T18:56:53Z","title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01155","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":"sha256:9392c3917262248d5e72f57786fbbbbd535aa3327881bbfcdb76d61b3fd38707","target":"record","created_at":"2026-05-18T00:28:40Z","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":"b029e7b852bd4077b54c44d7e0e27de230689dfc97e72b4d23b60ff512d1cd2d","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-04T18:56:53Z","title_canon_sha256":"3f5f9aee0e3d8e3c374e8656b95f176230db156fe43a904a24ad554645c8c41b"},"schema_version":"1.0","source":{"id":"1704.01155","kind":"arxiv","version":2}},"canonical_sha256":"d4efc20e07a23a3b302983f4612527ea1a482ec87a49926136f96abe259a3bcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4efc20e07a23a3b302983f4612527ea1a482ec87a49926136f96abe259a3bcc","first_computed_at":"2026-05-18T00:28:40.957495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:40.957495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T7IqX2QlAYnpckHNvLfsi/ixzd/nRjypwPg1MSEFN5sDpweAJaarNHzNc57znOlyvBPolE+3eFfcDV93sE0HBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:40.958213Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.01155","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9392c3917262248d5e72f57786fbbbbd535aa3327881bbfcdb76d61b3fd38707","sha256:cc5494c3a47093ba34eb9d966b34fab08e1ed7b688832cb65021cc5d8d3e9135"],"state_sha256":"2f0d949fbc29ee82de8be43719bef4c8e26c8efb201cb7295e61ee066a218676"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SbTDV5E80pxDopJNPtiOqBiODBnoLAqbDHtgDINpdtPxIEvG8HpI8xBJCeBiciOE0nMVPHkb/Fwi1hbqhOtqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T08:13:05.087165Z","bundle_sha256":"471fa5224bad687a7fe51ea3334a41025f751687e9bf880f681547c0f1d3f33e"}}