{"total":29,"rows":[{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49,"area":"safety"},{"id":"2510.19207","title":"Defending Against Prompt Injection with DataFilter","created":"2025-10-22","cited_by_count":35,"area":"safety"},{"id":"2502.01042","title":"SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals","created":"2025-02-03","cited_by_count":29,"area":"safety"},{"id":"2503.10566","title":"ASIDE: Architectural Separation of Instructions and Data in Language Models","created":"2025-03-13","cited_by_count":24,"area":"safety"},{"id":"2505.11541","title":"MorphMark: Flexible Adaptive Watermarking for Large Language Models","created":"2025-05-14","cited_by_count":24,"area":"safety"},{"id":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23,"area":"safety"},{"id":"2503.00596","title":"BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge","created":"2025-03-01","cited_by_count":18,"area":"safety"},{"id":"2502.04204","title":"Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence","created":"2025-02-06","cited_by_count":14,"area":"safety"},{"id":"2503.08195","title":"Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation","created":"2025-03-11","cited_by_count":14,"area":"safety"},{"id":"2509.02820","title":"Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs","created":"2025-09-02","cited_by_count":11,"area":"safety"},{"id":"2501.16497","title":"Smoothed Embeddings for Robust Language Models","created":"2025-01-27","cited_by_count":8,"area":"safety"},{"id":"2605.06161","title":"Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges","created":"2026-05-07","cited_by_count":8,"area":"safety"},{"id":"2505.15656","title":"Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!","created":"2025-05-21","cited_by_count":5,"area":"safety"},{"id":"2510.01088","title":"Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2602.11495","title":"Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models","created":"2026-02-12","cited_by_count":4,"area":"safety"},{"id":"2604.08169","title":"Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2603.03323","title":"Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement","created":"2026-02-10","cited_by_count":3,"area":"safety"},{"id":"2608.21500","title":"SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation","created":"2026-08-21","cited_by_count":3,"area":"safety"},{"id":"2603.10068","title":"ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models","created":"2026-03-10","cited_by_count":1,"area":"safety"},{"id":"2604.12817","title":"Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory","created":"2026-04-14","cited_by_count":1,"area":"safety"},{"id":"2604.27861","title":"TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning","created":"2026-04-30","cited_by_count":1,"area":"safety"},{"id":"2609.25049","title":"Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration","created":"2026-09-06","cited_by_count":1,"area":"safety"},{"id":"2502.05291","title":"Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet","created":"2025-02-07","cited_by_count":0,"area":"safety"},{"id":"2602.02027","title":"Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron","created":"2026-02-02","cited_by_count":0,"area":"safety"},{"id":"2605.10611","title":"Re-Triggering Safeguards within LLMs for Jailbreak Detection","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.19321","title":"Exploring and Developing a Pre-Model Safeguard with Draft Models","created":"2026-05-19","cited_by_count":0,"area":"safety"},{"id":"2608.08212","title":"Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment","created":"2026-08-08","cited_by_count":0,"area":"safety"},{"id":"2609.21088","title":"Origin Is All You Need: Provenance-Aware Transformers for Structural Trust-Boundary Separation","created":"2026-09-17","cited_by_count":0,"area":"safety"},{"id":"2609.34514","title":"How to Tame a Multi-Headed Hydra? Adaptive Multi-Category Safety Steering for Large Language Models","created":"2026-09-28","cited_by_count":0,"area":"safety"}],"next_cursor":null}