{"total":36,"rows":[{"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":"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":"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":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18,"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":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2510.07985","title":"Fewer Weights, More Problems: A Practical Attack on LLM Pruning","created":"2025-10-09","cited_by_count":7,"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":"2505.16789","title":"Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2606.32038","title":"Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2606.29604","title":"Mechanistically Eliciting Latent Behaviors in Language Models","created":"2026-06-28","cited_by_count":3,"area":null},{"id":"2608.28327","title":"Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers","created":"2026-08-28","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":"2506.23296","title":"Securing AI Systems: A Guide to Known Attacks and Impacts","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2510.12117","title":"Locket: Robust Feature-Locking Technique for Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2511.08484","title":"Patching LLM Like Software: A Lightweight Method for Improving Safety Policy in Large Language Models","created":"2025-11-11","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":"2606.03344","title":"RogueMerge: Robust and Unified Attacks against LLM Model Merging","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.05817","title":"Consistency Training Along the Transformer Stack","created":"2026-06-04","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":"2506.22492","title":"Report on NSF Workshop on Science of Safe AI","created":"2025-06-24","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":"2604.02372","title":"Backdoor Attacks on Decentralised Post-Training","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.14194","title":"GradShield: Alignment Preserving Finetuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.15152","title":"Widening the Gap: Exploiting LLM Quantization via Outlier Injection","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.30819","title":"AI-Generated PowerShell Malware: An Experimental Framework and Dataset","created":"2026-06-29","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":"2608.31105","title":"BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.10142","title":"Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning","created":"2026-09-09","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":"2610.04316","title":"From Latent Space to Jacobian Space: Measuring, Evading, and Training Against Safety-Content Accessibility","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}