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
979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Control Protocols for Mitigating Covert Malicious Fine-Tuning Attacks from Internally Deployed Agents▼4.3k2.00
[PDF]GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention▼4.3k2.00
[PDF]ARMOR: Agentic Red-Teaming with Memory-Optimized Retrieval for Autonomous Jailbreaking of Frontier Language Models▼1611.50
[PDF]Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring▼1.2k3.00
[PDF]All you need to break LLMs are Black-Box, Adapting, Efficient, Transferable, Harmful, Applicable … Attacks▲13k2.33
[PDF]Financial Fragility in Societies of LLM Agents: Coordination Failures and Stabilizing Mechanisms▲3.0k2.33
[PDF]Risk Lies in the Relations: Relation-Aware Collaboration Graph Defense for LLM Multi-Agent Systems▲3942.67
[PDF]Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play▼1.2k1.67
[PDF]Mind the Modality Gap: From Constitutional AI to Contextual Policy-Alignment Through Language Bridging▲13k2.33
[PDF]SafetyTransfer: Distilling Harmful and Harmless Discrimination for Selective Refusal in Small Language Models▼4.3k2.00
[PDF]Hyperbolic Detoxification for Vision-Language Model Safety via Intent-Risk Calibration▼5.8k2.33
[PDF]The Sins of the Designer: Weight Generators Transmit Judge Bias to Models That Never Saw a Biased Example▼1.2k1.67
Withdrawn or desk rejected (231)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00