{"total":60,"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":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86,"area":null},{"id":"2410.24190","title":"Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters","created":"2024-10-31","cited_by_count":71,"area":null},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"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":"2504.20984","title":"ACE: A Security Architecture for LLM-Integrated App Systems","created":"2025-04-29","cited_by_count":55,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"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":"2506.14261","title":"RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?","created":"2025-06-17","cited_by_count":24,"area":null},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"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":"2506.00911","title":"Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models","created":"2025-06-01","cited_by_count":12,"area":null},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2505.22586","title":"Precise In-Parameter Concept Erasure in Large Language Models","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2510.16171","title":"Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2503.05628","title":"Superintelligence Strategy: Expert Version","created":"2025-03-07","cited_by_count":7,"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":"2506.18932","title":"AI Safety vs. AI Security: Demystifying the Distinction and Boundaries","created":"2025-06-21","cited_by_count":5,"area":null},{"id":"2601.19768","title":"GAVEL: Towards Rule-Based Safety Through Activation Monitoring","created":"2026-01-27","cited_by_count":5,"area":null},{"id":"2506.07330","title":"JavelinGuard: Low-Cost Transformer Architectures for LLM Security","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2406.17809","title":"Towards a Science Exocortex","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2409.06927","title":"Representation Tuning","created":"2024-09-11","cited_by_count":3,"area":null},{"id":"2508.11281","title":"ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2601.00968","title":"Explainability-Guided Defense: Attribution-Aware Model Refinement Against Adversarial Data Attacks","created":"2026-01-02","cited_by_count":3,"area":null},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2606.00341","title":"ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2502.05242","title":"Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2606.05290","title":"Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.09053","title":"An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?","created":"2026-07-10","cited_by_count":2,"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":"2504.15499","title":"Guillotine: Hypervisors for Isolating Malicious AIs","created":"2025-04-22","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":"2509.05608","title":"BinaryShield: Cross-Service Threat Intelligence in LLM Services using Privacy-Preserving Fingerprints","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2510.06527","title":"Wide Neural Networks as a Baseline for the Computational No-Coincidence Conjecture","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.11235","title":"AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?","created":"2025-10-13","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":"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":"2512.00725","title":"ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering","created":"2025-11-30","cited_by_count":1,"area":null},{"id":"2512.11783","title":"Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2602.16980","title":"Discovering Universal Activation Directions for PII Leakage in Language Models","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2606.00160","title":"DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2609.00092","title":"Safin-1: Safety from Within through Memory-Native State Evolution","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2503.00224","title":"\\`A la recherche du sens perdu: your favourite LLM might have more to say than you can understand","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2505.22287","title":"New Tools are Needed for Tracking Adherence to AI Model Behavioral Use Clauses","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2512.03720","title":"Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs","created":"2025-12-03","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":"2605.05630","title":"One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.03634","title":"The Role of Rigor in Artificial Intelligence","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.04322","title":"DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.18093","title":"Abliteration Mitigation via Refusal Aliases","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2609.04721","title":"Locating and Steering Refusal Beyond Attention","created":"2026-09-04","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},{"id":"2609.39701","title":"Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}