{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WCUNEOO26JRK66JSHD4C7QPODB","short_pith_number":"pith:WCUNEOO2","schema_version":"1.0","canonical_sha256":"b0a8d239daf262af793238f82fc1ee1866075d4029e6c6510b1f3ad355559d86","source":{"kind":"arxiv","id":"2607.13453","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Prompting Framework for AI Safety Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Anirban Chatterjee, Kunal Banerjee, Yash Bhatnagar","submitted_at":"2026-07-15T05:26:43Z","abstract_excerpt":"Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actors -- adversarial prompt attack (APA) being one of the most prominent examples of such threats. This paper presents the implementation of an Adversarial Prompting Framework (APF) for a comprehensive assessment of AI safety. The framework systematically evaluates the resilience of the AI model through the generation of structured adversarial prompts at m"},"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":"2607.13453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-15T05:26:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fca9d3917a8d10333998846e8e042a37d662fb3f8c88056dc7adf853bbeca733","abstract_canon_sha256":"bfd99a1e0a0e15e4949b1454da65178594016a25c8127ddcebed610f3d37f0ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:13.637035Z","signature_b64":"KCdUUU1qj3czTv67LAWJWkoq09F4VKc3+bH+tCwXmEIVp8/swC2xVTvnV0MOF9Mvrk7E3alQcEeL8bL2nvDQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0a8d239daf262af793238f82fc1ee1866075d4029e6c6510b1f3ad355559d86","last_reissued_at":"2026-07-16T01:22:13.636143Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:13.636143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Prompting Framework for AI Safety Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Anirban Chatterjee, Kunal Banerjee, Yash Bhatnagar","submitted_at":"2026-07-15T05:26:43Z","abstract_excerpt":"Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actors -- adversarial prompt attack (APA) being one of the most prominent examples of such threats. This paper presents the implementation of an Adversarial Prompting Framework (APF) for a comprehensive assessment of AI safety. The framework systematically evaluates the resilience of the AI model through the generation of structured adversarial prompts at m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13453","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/2607.13453/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":"2607.13453","created_at":"2026-07-16T01:22:13.636627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13453v1","created_at":"2026-07-16T01:22:13.636627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13453","created_at":"2026-07-16T01:22:13.636627+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCUNEOO26JRK","created_at":"2026-07-16T01:22:13.636627+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCUNEOO26JRK66JS","created_at":"2026-07-16T01:22:13.636627+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCUNEOO2","created_at":"2026-07-16T01:22:13.636627+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/WCUNEOO26JRK66JSHD4C7QPODB","json":"https://pith.science/pith/WCUNEOO26JRK66JSHD4C7QPODB.json","graph_json":"https://pith.science/api/pith-number/WCUNEOO26JRK66JSHD4C7QPODB/graph.json","events_json":"https://pith.science/api/pith-number/WCUNEOO26JRK66JSHD4C7QPODB/events.json","paper":"https://pith.science/paper/WCUNEOO2"},"agent_actions":{"view_html":"https://pith.science/pith/WCUNEOO26JRK66JSHD4C7QPODB","download_json":"https://pith.science/pith/WCUNEOO26JRK66JSHD4C7QPODB.json","view_paper":"https://pith.science/paper/WCUNEOO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13453&json=true","fetch_graph":"https://pith.science/api/pith-number/WCUNEOO26JRK66JSHD4C7QPODB/graph.json","fetch_events":"https://pith.science/api/pith-number/WCUNEOO26JRK66JSHD4C7QPODB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCUNEOO26JRK66JSHD4C7QPODB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCUNEOO26JRK66JSHD4C7QPODB/action/storage_attestation","attest_author":"https://pith.science/pith/WCUNEOO26JRK66JSHD4C7QPODB/action/author_attestation","sign_citation":"https://pith.science/pith/WCUNEOO26JRK66JSHD4C7QPODB/action/citation_signature","submit_replication":"https://pith.science/pith/WCUNEOO26JRK66JSHD4C7QPODB/action/replication_record"}},"created_at":"2026-07-16T01:22:13.636627+00:00","updated_at":"2026-07-16T01:22:13.636627+00:00"}