{"total":17,"rows":[{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247,"area":"safety"},{"id":"2306.04634","title":"On the Reliability of Watermarks for Large Language Models","created":"2023-06-07","cited_by_count":189,"area":"safety"},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2406.08607","title":"Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference","created":"2024-06-12","cited_by_count":88,"area":"safety"},{"id":"2402.10052","title":"UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2404.11045","title":"Offset Unlearning for Large Language Models","created":"2024-04-17","cited_by_count":36,"area":"safety"},{"id":"2502.12197","title":"A Closer Look at System Prompt Robustness","created":"2025-02-15","cited_by_count":32,"area":"safety"},{"id":"2402.05864","title":"Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs","created":"2024-02-08","cited_by_count":22,"area":"safety"},{"id":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2504.17480","title":"Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation","created":"2025-04-24","cited_by_count":11,"area":"safety"},{"id":"2506.12097","title":"UCD: Unlearning in LLMs via Contrastive Decoding","created":"2025-06-12","cited_by_count":9,"area":"safety"},{"id":"2407.04151","title":"Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers","created":"2024-07-04","cited_by_count":5,"area":"safety"},{"id":"2505.24379","title":"Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM","created":"2025-05-30","cited_by_count":5,"area":"safety"},{"id":"2603.08234","title":"The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs","created":"2026-03-09","cited_by_count":1,"area":"safety"},{"id":"2606.12342","title":"ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing","created":"2026-06-10","cited_by_count":1,"area":"safety"},{"id":"2407.14206","title":"Watermark Smoothing Attacks against Language Models","created":"2024-07-19","cited_by_count":0,"area":"safety"},{"id":"2609.03844","title":"Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference","created":"2026-09-03","cited_by_count":0,"area":"safety"}],"next_cursor":null}