{"total":14,"rows":[{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72,"area":"safety"},{"id":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66,"area":"safety"},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2310.14480","title":"Attention-Enhancing Backdoor Attacks Against BERT-based Models","created":"2023-10-23","cited_by_count":32,"area":"safety"},{"id":"2502.15334","title":"Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment","created":"2025-02-21","cited_by_count":7,"area":"safety"},{"id":"2302.10291","title":"Can Large Language Models Change User Preference Adversarially?","created":"2023-01-05","cited_by_count":5,"area":"safety"},{"id":"2505.24232","title":"From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2512.21110","title":"Beyond Context: Large Language Models' Failure to Grasp Users' Intent","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"id":"2601.21695","title":"AtPatch: Debugging Transformers via Hot-Fixing Over-Attention","created":"2026-01-29","cited_by_count":1,"area":"safety"},{"id":"2603.23269","title":"Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs","created":"2026-03-24","cited_by_count":1,"area":"safety"},{"id":"2606.06320","title":"Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance","created":"2026-06-04","cited_by_count":1,"area":"safety"},{"id":"2601.20282","title":"Memory Retrieval in Transformers: Insights from The Encoding Specificity Principle","created":"2026-01-28","cited_by_count":0,"area":"safety"},{"id":"2602.19215","title":"Understanding Empirical Unlearning with Combinatorial Interpretability","created":"2026-02-22","cited_by_count":0,"area":"safety"},{"id":"2605.12128","title":"Metaphor Is Not All Attention Needs","created":"2026-05-12","cited_by_count":0,"area":"safety"}],"next_cursor":null}