{"total":40,"rows":[{"id":"2504.01550","title":"Representation Bending for Large Language Model Safety","created":"2025-04-02","cited_by_count":30,"area":"safety"},{"id":"2411.11114","title":"JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit","created":"2024-11-17","cited_by_count":22,"area":"safety"},{"id":"2510.14005","title":"PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features","created":"2025-10-15","cited_by_count":20,"area":"safety"},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2512.21008","title":"GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs","created":"2025-12-24","cited_by_count":11,"area":"safety"},{"id":"2604.18519","title":"LLM Safety From Within: Detecting Harmful Content with Internal Representations","created":"2026-04-20","cited_by_count":11,"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":"2503.09066","title":"Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States","created":"2025-03-12","cited_by_count":9,"area":"safety"},{"id":"2505.10838","title":"LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs","created":"2025-05-16","cited_by_count":7,"area":"safety"},{"id":"2502.19537","title":"No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms","created":"2025-02-26","cited_by_count":6,"area":"safety"},{"id":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2603.00498","title":"Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence","created":"2026-02-28","cited_by_count":6,"area":"safety"},{"id":"2410.10150","title":"Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting","created":"2024-10-14","cited_by_count":5,"area":"safety"},{"id":"2511.22047","title":"Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks","created":"2025-11-27","cited_by_count":5,"area":"safety"},{"id":"2502.16174","title":"Efficient LLM Moderation with Multi-Layer Latent Prototypes","created":"2025-02-22","cited_by_count":4,"area":"safety"},{"id":"2602.08741","title":"Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing","created":"2026-02-09","cited_by_count":4,"area":"safety"},{"id":"2501.02373","title":"BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors","created":"2025-01-04","cited_by_count":3,"area":"safety"},{"id":"2501.16534","title":"Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs","created":"2025-01-27","cited_by_count":3,"area":"safety"},{"id":"2505.04578","title":"Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization","created":"2025-05-07","cited_by_count":3,"area":"safety"},{"id":"2506.07356","title":"Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks","created":"2025-06-09","cited_by_count":2,"area":"safety"},{"id":"2508.09190","title":"Multi-Level Safety Continual Projection for Fine-Tuned Large Language Models without Retraining","created":"2025-08-08","cited_by_count":2,"area":"safety"},{"id":"2601.22620","title":"Layer-wise Swapping for Generalizable Multilingual Safety","created":"2026-01-30","cited_by_count":2,"area":"safety"},{"id":"2604.08297","title":"Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models","created":"2026-04-09","cited_by_count":2,"area":"safety"},{"id":"2511.19009","title":"Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2512.14751","title":"One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs","created":"2025-12-14","cited_by_count":1,"area":"safety"},{"id":"2602.15853","title":"A Lightweight Explainable Guardrail for Prompt Safety","created":"2026-01-24","cited_by_count":1,"area":"safety"},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2609.16204","title":"Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration","created":"2026-09-14","cited_by_count":1,"area":"safety"},{"id":"2510.13901","title":"RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMs","created":"2025-10-14","cited_by_count":0,"area":"safety"},{"id":"2511.04215","title":"Black-Box Guardrail Reverse-engineering Attack","created":"2025-11-06","cited_by_count":0,"area":"safety"},{"id":"2511.18933","title":"Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations","created":"2025-11-24","cited_by_count":0,"area":"safety"},{"id":"2601.15801","title":"Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models","created":"2026-01-22","cited_by_count":0,"area":"safety"},{"id":"2602.17696","title":"Can LLM Safety Be Ensured by Constraining Parameter Regions?","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2604.11663","title":"Why Do Large Language Models Generate Harmful Content?","created":"2026-04-13","cited_by_count":0,"area":"safety"},{"id":"2605.24550","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2606.05614","title":"Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack","created":"2026-06-04","cited_by_count":0,"area":"safety"},{"id":"2606.27709","title":"Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"id":"2609.13534","title":"Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models","created":"2026-09-11","cited_by_count":0,"area":"safety"},{"id":"2610.15218","title":"Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models","created":"2026-10-10","cited_by_count":0,"area":"safety"},{"id":"2610.19452","title":"Are You Reading the Right Thing? Rethinking Internal Signals for Prompt-Injection Detection","created":"2026-10-14","cited_by_count":0,"area":"safety"}],"next_cursor":null}