{"total":20,"rows":[{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2409.15154","title":"RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code","created":"2024-09-23","cited_by_count":28,"area":"safety"},{"id":"2502.09755","title":"Jailbreak Attack Initializations as Extractors of Compliance Directions","created":"2025-02-13","cited_by_count":10,"area":"safety"},{"id":"2407.20181","title":"Blockchain for Large Language Model Security and Safety: A Holistic Survey","created":"2024-07-26","cited_by_count":8,"area":"safety"},{"id":"2503.02776","title":"Implicit Bias in LLMs: A Survey","created":"2025-03-04","cited_by_count":8,"area":"safety"},{"id":"2404.02532","title":"Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game","created":"2024-04-03","cited_by_count":5,"area":"safety"},{"id":"2503.08919","title":"Backtracking for Safety","created":"2025-03-11","cited_by_count":4,"area":"safety"},{"id":"2409.04822","title":"Exploring Straightforward Conversational Red-Teaming","created":"2024-09-07","cited_by_count":3,"area":"safety"},{"id":"2503.23250","title":"Encrypted Prompt: Securing LLM Applications Against Unauthorized Actions","created":"2025-03-29","cited_by_count":3,"area":"safety"},{"id":"2505.13028","title":"Evaluating the efficacy of LLM Safety Solutions : The Palit Benchmark Dataset","created":"2025-05-19","cited_by_count":2,"area":"safety"},{"id":"2506.05594","title":"SoK: Are Watermarks in LLMs Ready for Deployment?","created":"2025-06-05","cited_by_count":2,"area":"safety"},{"id":"2508.08629","title":"Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk Assessment","created":"2025-08-12","cited_by_count":2,"area":"safety"},{"id":"2512.18244","title":"Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation","created":"2025-12-20","cited_by_count":2,"area":"safety"},{"id":"2509.16870","title":"DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems","created":"2025-09-21","cited_by_count":1,"area":"safety"},{"id":"2602.05252","title":"Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks","created":"2026-02-05","cited_by_count":1,"area":"safety"},{"id":"2606.27210","title":"Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes","created":"2026-06-25","cited_by_count":1,"area":"safety"},{"id":"2602.02280","title":"RACC: Representation-Aware Coverage Criteria for LLM Safety Testing","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2610.10276","title":"PatchBench: Measuring Collateral Damage in Activation Patching","created":"2026-10-07","cited_by_count":0,"area":"safety"}],"next_cursor":null}