{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6CIUHE7YCHQ7HLMJS2ZMEYUSZ7","short_pith_number":"pith:6CIUHE7Y","schema_version":"1.0","canonical_sha256":"f0914393f811e1f3ad8996b2c26292cfe13b6d611b75f4c4a8021071fd8df0ba","source":{"kind":"arxiv","id":"2410.02240","version":6},"attestation_state":"computed","paper":{"title":"SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lifeng Chen, Weibin Wu, Yuhang Cao, Zibin Zheng, Zihao Pan","submitted_at":"2024-10-03T06:25:53Z","abstract_excerpt":"Systems based on deep neural networks are vulnerable to adversarial attacks. Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic. Recent works have utilized the diffusion inversion process to map images into a latent space, where high-level semantics are manipulated by introducing perturbations. However, they often result in substantial semantic distortions in the denoised output and suffer from low efficiency. In this study, we propose a novel framework called "},"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":"2410.02240","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T06:25:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a42827ea64de3594c248ed475febd2bfeeea4c5799e16fa7cca3b7fffd9802cd","abstract_canon_sha256":"4109f2554d51eb6845ccc8c806083b610c5465ab8c708dc0b24d9bcf6ea52304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:55.906293Z","signature_b64":"JS3Xw5YY0VAV0YMcv+p8knGsOP4SN5ipFBuDDLM1C3a7VVeu2zFeXfv7sp9V9ZUjyAaxEdDKSmGsLCmGBk/yAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0914393f811e1f3ad8996b2c26292cfe13b6d611b75f4c4a8021071fd8df0ba","last_reissued_at":"2026-07-05T11:01:55.905753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:55.905753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lifeng Chen, Weibin Wu, Yuhang Cao, Zibin Zheng, Zihao Pan","submitted_at":"2024-10-03T06:25:53Z","abstract_excerpt":"Systems based on deep neural networks are vulnerable to adversarial attacks. Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic. Recent works have utilized the diffusion inversion process to map images into a latent space, where high-level semantics are manipulated by introducing perturbations. However, they often result in substantial semantic distortions in the denoised output and suffer from low efficiency. In this study, we propose a novel framework called "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02240","kind":"arxiv","version":6},"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/2410.02240/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":"2410.02240","created_at":"2026-07-05T11:01:55.905812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02240v6","created_at":"2026-07-05T11:01:55.905812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02240","created_at":"2026-07-05T11:01:55.905812+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CIUHE7YCHQ7","created_at":"2026-07-05T11:01:55.905812+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CIUHE7YCHQ7HLMJ","created_at":"2026-07-05T11:01:55.905812+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CIUHE7Y","created_at":"2026-07-05T11:01:55.905812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01511","citing_title":"Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7","json":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7.json","graph_json":"https://pith.science/api/pith-number/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/graph.json","events_json":"https://pith.science/api/pith-number/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/events.json","paper":"https://pith.science/paper/6CIUHE7Y"},"agent_actions":{"view_html":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7","download_json":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7.json","view_paper":"https://pith.science/paper/6CIUHE7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02240&json=true","fetch_graph":"https://pith.science/api/pith-number/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/action/storage_attestation","attest_author":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/action/author_attestation","sign_citation":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/action/citation_signature","submit_replication":"https://pith.science/pith/6CIUHE7YCHQ7HLMJS2ZMEYUSZ7/action/replication_record"}},"created_at":"2026-07-05T11:01:55.905812+00:00","updated_at":"2026-07-05T11:01:55.905812+00:00"}