NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
158 results for “keyword:"jailbreak"” in ICLR 2027. 38 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]JailbreakProfiler: Fine-Grained Attack Pattern Recognition and Open-Set Attribution for LLM Safety▼5.8k2.33
[PDF]The Perceptual Bandwidth Tax: Matched Evaluation of Emotion and Accent as Jailbreak Surfaces in End-to-End Audio-Language Models▲432.75
[PDF]KV Compression Cannot Double as a Jailbreak Defense: The Harmfulness-then-Refusal Trajectory Guides Token Deletion▼5.8k2.33
[PDF]A Jailbreak Success Coordinate Outside the Refusal Subspace: Decodable Before Generation, Reachable from the Input▼5.8k2.33
[PDF]Form Before Harm: Diagnosing the Semantic Influence of Jailbreak Formats with Activation Steering▼1.2k1.67
[PDF]Anchored but Not Protected: When Refusal Erodes During Fine-Tuning, and Whether Holding One Direction Stops It▲13k2.33
[PDF]Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models▲6.1k2.00
[PDF]Unified Hierarchical Red-Teaming: Strategy Search and Evidence-Guided Policy Evolution▼4.3k2.00
[PDF]Blackwell-Guided Logit Search (BLS): Optimizing Multi-Turn Jailbreaks with Subliminal Steering▼1.2k1.67
[PDF]Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of Audio-Language Models▼1.2k1.67
[PDF]Crescendo-Live: Multi-Turn Jailbreaks of Full-Duplex Speech Models in Live Calls and Their Defense with Daimonion▲3.0k2.50
[PDF]Beyond Jailbreak Rates: Harm Centric Evaluation of Multi Turn Jailbreak Attacks and Defenses▼4.3k2.00
[PDF]Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes▼1.2k1.67
[PDF]How Jailbreak Attacks Inform LLM Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions▼5.8k2.33
[PDF]ProbeFool: Evading LLM Jailbreak Activation Monitors with Probe-Agnostic Attention Routing▼4.3k2.00
[PDF]For Research Purpose Only - Jailbreaking Large Language Models with Jailbreaking Research▼13k2.00
[PDF]GenShield: Generalizable Visual Prompts for VLM Jailbreak Defense via Dual-View Adversarial Training▲3.0k2.33
[PDF]FSPO: Fast Adversarial Training against Jailbreak Attacks via Soft Prompt Optimization▼4.5k2.67
[PDF]LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs▲5103.00
Withdrawn or desk rejected (38)
[PDF]Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language ModelsWithdrawn2.00
[PDF]When Attribution Graphs Fail to Predict LLM Jailbreaks: Distinguishing Structural Signals, Causal Effects, and Behavioral SafetyWithdrawn1.67
[PDF]Same Request, Different Answer: How Conversation History Shapes the Decision to Refuse or ComplyWithdrawn2.00
[PDF]REFUSALTRACE: Sparse Activation Masking for Jailbreaking via Natural Refusal TrajectoriesWithdrawn2.00
[PDF]Non-Intrusive Safety Alignment for Vision-Language Models via Automated Output RewritingWithdrawn1.67