{"total":25,"rows":[{"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":"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":"2508.03153","title":"Estimating Worst-Case Frontier Risks of Open-Weight LLMs","created":"2025-08-05","cited_by_count":19,"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":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"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":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2601.22313","title":"Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2503.20848","title":"The Backfiring Effect of Weak AI Safety Regulation","created":"2025-03-26","cited_by_count":3,"area":null},{"id":"2512.01899","title":"Provably Safe Model Updates","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2503.16833","title":"The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2507.11544","title":"The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2605.14605","title":"A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2502.15720","title":"Training AI to be Loyal","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2510.27629","title":"Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2601.01584","title":"Steerability of Instrumental-Convergence Tendencies in LLMs","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2606.25059","title":"What Does It Mean to Break a Distillation Defense?","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.13039","title":"Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.22929","title":"Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety","created":"2026-07-24","cited_by_count":1,"area":null},{"id":"2507.10106","title":"BlueGlass: A Framework for Composite AI Safety","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2602.17418","title":"A Privacy by Design Framework for Large Language Model-Based Applications for Children","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2605.10777","title":"Locking Pretrained Weights via Deep Low-Rank Residual Distillation","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2609.00519","title":"The Safeguard Worked. Is the LLM System Safer?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.20027","title":"Can Data Attribution Filter Out Subliminal Learning? Not Reliably","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}