{"total":23,"rows":[{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2503.16248","title":"Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents","created":"2025-03-20","cited_by_count":24,"area":"safety"},{"id":"2410.10414","title":"On Calibration of LLM-based Guard Models for Reliable Content Moderation","created":"2024-10-14","cited_by_count":23,"area":"safety"},{"id":"2407.00869","title":"Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks","created":"2024-07-01","cited_by_count":19,"area":"safety"},{"id":"2506.01114","title":"Reconsidering LLM Uncertainty Estimation Methods in the Wild","created":"2025-06-01","cited_by_count":17,"area":"safety"},{"id":"2407.11282","title":"Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models","created":"2024-07-15","cited_by_count":13,"area":"safety"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2510.16794","title":"Black-box Optimization of LLM Outputs by Asking for Directions","created":"2025-10-19","cited_by_count":7,"area":"safety"},{"id":"2510.17210","title":"Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting","created":"2025-10-20","cited_by_count":6,"area":"safety"},{"id":"2405.10128","title":"Red Teaming Language Models for Processing Contradictory Dialogues","created":"2024-05-16","cited_by_count":3,"area":"safety"},{"id":"2502.09974","title":"Has My System Prompt Been Used? Large Language Model Prompt Membership Inference","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2602.04581","title":"Trust The Typical","created":"2026-02-04","cited_by_count":3,"area":"safety"},{"id":"2604.18775","title":"An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models","created":"2026-04-20","cited_by_count":2,"area":"safety"},{"id":"2504.01533","title":"LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution","created":"2025-04-02","cited_by_count":1,"area":"safety"},{"id":"2503.00600","title":"Semantic Integrity Constraints: Declarative Guardrails for AI-Augmented Data Processing Systems","created":"2025-03-01","cited_by_count":0,"area":"safety"},{"id":"2602.08877","title":"Stress-Testing Alignment Audits With Prompt-Level Strategic Deception","created":"2026-02-09","cited_by_count":0,"area":"safety"},{"id":"2604.00228","title":"Do Language Models Know When They'll Refuse? Probing Introspective Awareness of Safety Boundaries","created":"2026-03-31","cited_by_count":0,"area":"safety"},{"id":"2604.16606","title":"SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models","created":"2026-04-17","cited_by_count":0,"area":"safety"},{"id":"2608.12652","title":"Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection","created":"2026-08-12","cited_by_count":0,"area":"safety"},{"id":"2608.23663","title":"Confidently Wrong, Silently So: Auditing Undetectable Failures of a Deployed On-Device Language Model","created":"2026-08-24","cited_by_count":0,"area":"safety"},{"id":"2610.08540","title":"Toward Alignment Scaling Laws: A Framework and First Preregistered Measurements","created":"2026-10-06","cited_by_count":0,"area":"safety"},{"id":"2610.08840","title":"Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding","created":"2026-09-30","cited_by_count":0,"area":"safety"}],"next_cursor":null}