{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BVNVUR5LHBKUMRSK2VSJOY6VWV","short_pith_number":"pith:BVNVUR5L","schema_version":"1.0","canonical_sha256":"0d5b5a47ab385546464ad5649763d5b542f26b012af43f39249aa7f4cf33c697","source":{"kind":"arxiv","id":"2006.07700","version":3},"attestation_state":"computed","paper":{"title":"Defensive Approximation: Securing CNNs using Approximate Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Amira Guesmi, Ihsen Alouani, Khaled Khasawneh, Mohamed Abid, Mouna Baklouti, Nael Abu-Ghazaleh, Tarek Frikha","submitted_at":"2020-06-13T18:58:25Z","abstract_excerpt":"In the past few years, an increasing number of machine-learning and deep learning structures, such as Convolutional Neural Networks (CNNs), have been applied to solving a wide range of real-life problems. However, these architectures are vulnerable to adversarial attacks. In this paper, we propose for the first time to use hardware-supported approximate computing to improve the robustness of machine learning classifiers. We show that our approximate computing implementation achieves robustness across a wide range of attack scenarios. Specifically, for black-box and grey-box attack scenarios, w"},"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":"2006.07700","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-06-13T18:58:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4cb3e5afe5012867a8c5fca67131f8e287292dbb1618eed5b2522f8a30f69d01","abstract_canon_sha256":"98dc17fc08937629d92e890da69d4b4293569f2dba72c8b209bb31bd537ff938"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:01:33.238025Z","signature_b64":"mwDCd1K+phct/MBVu05mG2GiciOequN+tYB0wZqiX2j+uTd/iIPsGzY586tkIVisKmVdjId16bGLUfOHJ4RbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d5b5a47ab385546464ad5649763d5b542f26b012af43f39249aa7f4cf33c697","last_reissued_at":"2026-07-05T03:01:33.237440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:01:33.237440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defensive Approximation: Securing CNNs using Approximate Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Amira Guesmi, Ihsen Alouani, Khaled Khasawneh, Mohamed Abid, Mouna Baklouti, Nael Abu-Ghazaleh, Tarek Frikha","submitted_at":"2020-06-13T18:58:25Z","abstract_excerpt":"In the past few years, an increasing number of machine-learning and deep learning structures, such as Convolutional Neural Networks (CNNs), have been applied to solving a wide range of real-life problems. However, these architectures are vulnerable to adversarial attacks. In this paper, we propose for the first time to use hardware-supported approximate computing to improve the robustness of machine learning classifiers. We show that our approximate computing implementation achieves robustness across a wide range of attack scenarios. Specifically, for black-box and grey-box attack scenarios, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07700","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.07700/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2006.07700","created_at":"2026-07-05T03:01:33.237520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07700v3","created_at":"2026-07-05T03:01:33.237520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07700","created_at":"2026-07-05T03:01:33.237520+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVNVUR5LHBKU","created_at":"2026-07-05T03:01:33.237520+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVNVUR5LHBKUMRSK","created_at":"2026-07-05T03:01:33.237520+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVNVUR5L","created_at":"2026-07-05T03:01:33.237520+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/BVNVUR5LHBKUMRSK2VSJOY6VWV","json":"https://pith.science/pith/BVNVUR5LHBKUMRSK2VSJOY6VWV.json","graph_json":"https://pith.science/api/pith-number/BVNVUR5LHBKUMRSK2VSJOY6VWV/graph.json","events_json":"https://pith.science/api/pith-number/BVNVUR5LHBKUMRSK2VSJOY6VWV/events.json","paper":"https://pith.science/paper/BVNVUR5L"},"agent_actions":{"view_html":"https://pith.science/pith/BVNVUR5LHBKUMRSK2VSJOY6VWV","download_json":"https://pith.science/pith/BVNVUR5LHBKUMRSK2VSJOY6VWV.json","view_paper":"https://pith.science/paper/BVNVUR5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07700&json=true","fetch_graph":"https://pith.science/api/pith-number/BVNVUR5LHBKUMRSK2VSJOY6VWV/graph.json","fetch_events":"https://pith.science/api/pith-number/BVNVUR5LHBKUMRSK2VSJOY6VWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVNVUR5LHBKUMRSK2VSJOY6VWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVNVUR5LHBKUMRSK2VSJOY6VWV/action/storage_attestation","attest_author":"https://pith.science/pith/BVNVUR5LHBKUMRSK2VSJOY6VWV/action/author_attestation","sign_citation":"https://pith.science/pith/BVNVUR5LHBKUMRSK2VSJOY6VWV/action/citation_signature","submit_replication":"https://pith.science/pith/BVNVUR5LHBKUMRSK2VSJOY6VWV/action/replication_record"}},"created_at":"2026-07-05T03:01:33.237520+00:00","updated_at":"2026-07-05T03:01:33.237520+00:00"}