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
28 results for “keyword:"jailbreaking"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[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]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]Interaction Collapses Safety: On the Query-Access Limits of Jailbreak-Robust Generation▲4002.67
[PDF]TRAIL: Trajectory-Aware Navigation over Latent Hazard Landscapes for Multi-Turn LLM Jailbreaking▲3.0k2.33
[PDF]From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents▲9.2k2.67
[PDF]ARMOR: Agentic Red-Teaming with Memory-Optimized Retrieval for Autonomous Jailbreaking of Frontier Language Models▼1601.50
Withdrawn or desk rejected (4)
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected