{"total":29,"rows":[{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"id":"2409.20089","title":"Robust LLM safeguarding via refusal feature adversarial training","created":"2024-09-30","cited_by_count":64,"area":null},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2502.20968","title":"Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs","created":"2025-02-28","cited_by_count":22,"area":null},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20,"area":null},{"id":"2406.11096","title":"The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models","created":"2024-06-16","cited_by_count":19,"area":null},{"id":"2506.08473","title":"AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin","created":"2025-06-10","cited_by_count":19,"area":null},{"id":"2410.13211","title":"Estimating the Probabilities of Rare Outputs in Language Models","created":"2024-10-17","cited_by_count":16,"area":null},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2506.24068","title":"STACK: Adversarial Attacks on LLM Safeguard Pipelines","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2502.06470","title":"A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2502.11910","title":"Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2503.01345","title":"Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2405.17130","title":"Explaining the role of Intrinsic Dimensionality in Adversarial Training","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2505.19397","title":"Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2502.16366","title":"A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2604.24332","title":"Mitigating Error Amplification in Fast Adversarial Training","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2605.12813","title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2607.18454","title":"Estimating Rare Events in Language Models with Proper Evaluation","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2601.16200","title":"Feature-Space Smoothing: Certified Robustness of Deep Representations","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2602.15238","title":"Closing the Distribution Gap in Adversarial Training for LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.24350","title":"Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2607.28959","title":"Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.24969","title":"Rare Event Estimation via Iterative Unalignment","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.13928","title":"AI Models Can Provably Hide Arbitrary Capabilities","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}