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
18 results for “keyword:"jailbreak defense"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]KV Compression Cannot Double as a Jailbreak Defense: The Harmfulness-then-Refusal Trajectory Guides Token Deletion▼5.8k2.33
[PDF]Beyond Jailbreak Rates: Harm Centric Evaluation of Multi Turn Jailbreak Attacks and Defenses▼4.3k2.00
[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]Trajectory-Guided Rotation Steering for Jailbreak Defense in Audio Large Language Models▼5.8k2.33
[PDF]HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models▼1.2k1.67
[PDF]K-Shield: Improving the Safety-Utility Trade-off in Refusal Steering with Local Null-Space Constraints▼4.5k2.67
[PDF]Being Trapped then Mitigated: Defending Malicious Jailbreak Prompts via Embedded Honeypots in Text-to-Image Models▼5.8k2.33
Withdrawn or desk rejected (7)
[PDF]Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language ModelsWithdrawn2.00
[PDF]Non-Intrusive Safety Alignment for Vision-Language Models via Automated Output RewritingWithdrawn1.67
[PDF]Defending Large Language Models Against Diverse Jailbreak Attacks via Multi-Concept DetectionWithdrawn1.33