{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DUNXFLW3IRNSYEOOQV2IFPGAOJ","short_pith_number":"pith:DUNXFLW3","schema_version":"1.0","canonical_sha256":"1d1b72aedb445b2c11ce857482bcc0726ff7f6dafc2dbcfc544fa4a5fe4f8445","source":{"kind":"arxiv","id":"2312.04035","version":1},"attestation_state":"computed","paper":{"title":"Defense against ML-based Power Side-channel Attacks on DNN Accelerators with Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Chip Hong Chang, Tianwei Zhang, Xiaobei Yan","submitted_at":"2023-12-07T04:38:01Z","abstract_excerpt":"Artificial Intelligence (AI) hardware accelerators have been widely adopted to enhance the efficiency of deep learning applications. However, they also raise security concerns regarding their vulnerability to power side-channel attacks (SCA). In these attacks, the adversary exploits unintended communication channels to infer sensitive information processed by the accelerator, posing significant privacy and copyright risks to the models. Advanced machine learning algorithms are further employed to facilitate the side-channel analysis and exacerbate the privacy issue of AI accelerators. Traditio"},"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":"2312.04035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-12-07T04:38:01Z","cross_cats_sorted":[],"title_canon_sha256":"1efab358d37c02c24028db7bbf7b3806bf797e2625b5050dc68cff06722bc3e4","abstract_canon_sha256":"4bfc32224fc4c57ab497d159dc691811c60ac9ac014b3645fa405c417ddc648d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:18.496646Z","signature_b64":"P5D3ymzsBRRFsRjf/fGGhD5j2U8u9qV4USJyWuB0rnGEOlOdTOixHf6uuGUwqk10qV6hLGM6VCzq7HdvjVraCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d1b72aedb445b2c11ce857482bcc0726ff7f6dafc2dbcfc544fa4a5fe4f8445","last_reissued_at":"2026-07-05T07:21:18.496187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:18.496187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defense against ML-based Power Side-channel Attacks on DNN Accelerators with Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Chip Hong Chang, Tianwei Zhang, Xiaobei Yan","submitted_at":"2023-12-07T04:38:01Z","abstract_excerpt":"Artificial Intelligence (AI) hardware accelerators have been widely adopted to enhance the efficiency of deep learning applications. However, they also raise security concerns regarding their vulnerability to power side-channel attacks (SCA). In these attacks, the adversary exploits unintended communication channels to infer sensitive information processed by the accelerator, posing significant privacy and copyright risks to the models. Advanced machine learning algorithms are further employed to facilitate the side-channel analysis and exacerbate the privacy issue of AI accelerators. Traditio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04035","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.04035/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":"2312.04035","created_at":"2026-07-05T07:21:18.496243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04035v1","created_at":"2026-07-05T07:21:18.496243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04035","created_at":"2026-07-05T07:21:18.496243+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUNXFLW3IRNS","created_at":"2026-07-05T07:21:18.496243+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUNXFLW3IRNSYEOO","created_at":"2026-07-05T07:21:18.496243+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUNXFLW3","created_at":"2026-07-05T07:21:18.496243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22441","citing_title":"A Constant-Time Implementation Methodology for Activation Functions on Microcontrollers","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22935","citing_title":"Secure eFPGA-Enabled Edge LLM Inference: Architectural and Hardware Countermeasures","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ","json":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ.json","graph_json":"https://pith.science/api/pith-number/DUNXFLW3IRNSYEOOQV2IFPGAOJ/graph.json","events_json":"https://pith.science/api/pith-number/DUNXFLW3IRNSYEOOQV2IFPGAOJ/events.json","paper":"https://pith.science/paper/DUNXFLW3"},"agent_actions":{"view_html":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ","download_json":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ.json","view_paper":"https://pith.science/paper/DUNXFLW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04035&json=true","fetch_graph":"https://pith.science/api/pith-number/DUNXFLW3IRNSYEOOQV2IFPGAOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DUNXFLW3IRNSYEOOQV2IFPGAOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ/action/storage_attestation","attest_author":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ/action/author_attestation","sign_citation":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ/action/citation_signature","submit_replication":"https://pith.science/pith/DUNXFLW3IRNSYEOOQV2IFPGAOJ/action/replication_record"}},"created_at":"2026-07-05T07:21:18.496243+00:00","updated_at":"2026-07-05T07:21:18.496243+00:00"}