{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TWSO6CAKIXDIVUMRXRNJ455R33","short_pith_number":"pith:TWSO6CAK","schema_version":"1.0","canonical_sha256":"9da4ef080a45c68ad191bc5a9e77b1decd49fb8a6cc69fe9d865c0f0e43a9245","source":{"kind":"arxiv","id":"1811.12673","version":3},"attestation_state":"computed","paper":{"title":"ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hassan Foroosh, Xiaochun Cao, Xiaojun Jia, Xingxing Wei","submitted_at":"2018-11-30T08:56:30Z","abstract_excerpt":"Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an end-to-end image compression model to defend adversarial examples: \\textbf{ComDefend}. The proposed model consists of a compression convolutional neural network (ComCNN) and a reconstruction convolutional neural network (ResCNN). The ComCNN is used to maintain the structure information of the original image and purify adversarial perturbations. And the ResCNN is "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1811.12673","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-30T08:56:30Z","cross_cats_sorted":[],"title_canon_sha256":"2922c6bebae6e27f9a68d34619bb87cb62a09199a696f44a8dbb415b26c87ece","abstract_canon_sha256":"38a182914ca2c0c3cdbea3093bf4c8cb6586cda9b7095d30be1ff0f506334d9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:53.663188Z","signature_b64":"nil9Cu7cFIJcV1OETqxbquG8krd9Jc/JOc+NzF8Vex8mz4dsDsv4XlQtnW3iQ9YVSZVy/vxvMXN5CfjXXsRdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9da4ef080a45c68ad191bc5a9e77b1decd49fb8a6cc69fe9d865c0f0e43a9245","last_reissued_at":"2026-05-17T23:41:53.662778Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:53.662778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hassan Foroosh, Xiaochun Cao, Xiaojun Jia, Xingxing Wei","submitted_at":"2018-11-30T08:56:30Z","abstract_excerpt":"Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an end-to-end image compression model to defend adversarial examples: \\textbf{ComDefend}. The proposed model consists of a compression convolutional neural network (ComCNN) and a reconstruction convolutional neural network (ResCNN). The ComCNN is used to maintain the structure information of the original image and purify adversarial perturbations. And the ResCNN is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12673","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1811.12673","created_at":"2026-05-17T23:41:53.662844+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12673v3","created_at":"2026-05-17T23:41:53.662844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12673","created_at":"2026-05-17T23:41:53.662844+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWSO6CAKIXDI","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWSO6CAKIXDIVUMR","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWSO6CAK","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33","json":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33.json","graph_json":"https://pith.science/api/pith-number/TWSO6CAKIXDIVUMRXRNJ455R33/graph.json","events_json":"https://pith.science/api/pith-number/TWSO6CAKIXDIVUMRXRNJ455R33/events.json","paper":"https://pith.science/paper/TWSO6CAK"},"agent_actions":{"view_html":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33","download_json":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33.json","view_paper":"https://pith.science/paper/TWSO6CAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12673&json=true","fetch_graph":"https://pith.science/api/pith-number/TWSO6CAKIXDIVUMRXRNJ455R33/graph.json","fetch_events":"https://pith.science/api/pith-number/TWSO6CAKIXDIVUMRXRNJ455R33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33/action/storage_attestation","attest_author":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33/action/author_attestation","sign_citation":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33/action/citation_signature","submit_replication":"https://pith.science/pith/TWSO6CAKIXDIVUMRXRNJ455R33/action/replication_record"}},"created_at":"2026-05-17T23:41:53.662844+00:00","updated_at":"2026-05-17T23:41:53.662844+00:00"}