{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F4AD3VT3AE6JLFZJ77JKNLRBUO","short_pith_number":"pith:F4AD3VT3","schema_version":"1.0","canonical_sha256":"2f003dd67b013c959729ffd2a6ae21a38557c3453316a9c73a439da4df338f84","source":{"kind":"arxiv","id":"2410.20911","version":2},"attestation_state":"computed","paper":{"title":"Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese","submitted_at":"2024-10-28T10:43:34Z","abstract_excerpt":"Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense strategy tailored to counter LLM-driven cyberattacks. We introduce Mantis, a defensive framework that exploits LLMs' susceptibility to adversarial inputs to undermine malicious operations. Upon detecting an automated cyberattack, Mantis plants carefully crafted inputs into system responses, leading the attacker's LLM to disrupt their own operations (passive defense) or even compromise the attacker's machine (ac"},"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":"2410.20911","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-28T10:43:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"222b6184e8f1b3a32afceb6c5ce75c51850af59b6241c1d143044f2b6c49ccd6","abstract_canon_sha256":"2283e72d2c3b0ad7938c6f5da0ce516d62697b1dc702b58a14e4689e3f7d37a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:49.272647Z","signature_b64":"0kFW7x/JXK31aUblXZFU9lv5dVQbmTnLi4arcSOp8pwn+UAxMaywHhkqduZ8mC+4sNuBqE0IuNhSuFvTvgB4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f003dd67b013c959729ffd2a6ae21a38557c3453316a9c73a439da4df338f84","last_reissued_at":"2026-07-05T09:36:49.272168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:49.272168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese","submitted_at":"2024-10-28T10:43:34Z","abstract_excerpt":"Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense strategy tailored to counter LLM-driven cyberattacks. We introduce Mantis, a defensive framework that exploits LLMs' susceptibility to adversarial inputs to undermine malicious operations. Upon detecting an automated cyberattack, Mantis plants carefully crafted inputs into system responses, leading the attacker's LLM to disrupt their own operations (passive defense) or even compromise the attacker's machine (ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20911","kind":"arxiv","version":2},"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/2410.20911/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":"2410.20911","created_at":"2026-07-05T09:36:49.272222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20911v2","created_at":"2026-07-05T09:36:49.272222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20911","created_at":"2026-07-05T09:36:49.272222+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4AD3VT3AE6J","created_at":"2026-07-05T09:36:49.272222+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4AD3VT3AE6JLFZJ","created_at":"2026-07-05T09:36:49.272222+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4AD3VT3","created_at":"2026-07-05T09:36:49.272222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24402","citing_title":"Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20470","citing_title":"Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20470","citing_title":"Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18248","citing_title":"Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14317","citing_title":"Challenges and Future Directions in Agentic Reverse Engineering Systems","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18248","citing_title":"Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO","json":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO.json","graph_json":"https://pith.science/api/pith-number/F4AD3VT3AE6JLFZJ77JKNLRBUO/graph.json","events_json":"https://pith.science/api/pith-number/F4AD3VT3AE6JLFZJ77JKNLRBUO/events.json","paper":"https://pith.science/paper/F4AD3VT3"},"agent_actions":{"view_html":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO","download_json":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO.json","view_paper":"https://pith.science/paper/F4AD3VT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20911&json=true","fetch_graph":"https://pith.science/api/pith-number/F4AD3VT3AE6JLFZJ77JKNLRBUO/graph.json","fetch_events":"https://pith.science/api/pith-number/F4AD3VT3AE6JLFZJ77JKNLRBUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO/action/storage_attestation","attest_author":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO/action/author_attestation","sign_citation":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO/action/citation_signature","submit_replication":"https://pith.science/pith/F4AD3VT3AE6JLFZJ77JKNLRBUO/action/replication_record"}},"created_at":"2026-07-05T09:36:49.272222+00:00","updated_at":"2026-07-05T09:36:49.272222+00:00"}