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979 results for “keyword:"safety"” in ICLR 2027. 231 withdrawn or desk rejected listed apart.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]Interactive Monitoring: Can Questioning Mitigate Misbehavior While Preserving Task Utility?▼1.2k3.00
[PDF]Mitigating Deceptive Behaviour in Large Language Models through Alignment and Unlearning Interventions▼5.8k2.33
[PDF]PEGAS: Security Assessment of Power Grid Agents through Physics-informed Evolutionary Graph Adversarial Search▲3952.67
[PDF]Revealing Hidden Intent for Defending Text-to-Image Models against Adversarial Attacks▲3.0k2.33
[PDF]Know Your Target before Striking: A Profile-Aware Adaptive Jailbreaking Framework for LLMs▼4.3k2.00
[PDF]ASCENT: First-Order Optimal Fine-Tuning with Recalibration for Safety–Utility Co-Enhancement▲14k3.00
[PDF]DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection▲1.7k3.33
[PDF]Reference-KL Hijacking: Reference Poisoning Attacks in Distributed LLM Reinforcement Learning Frameworks▼4.3k2.00
[PDF]From Prompt Injection to Persistent Control: Defending Agentic Workspaces Against Trojan Backdoors▼1.2k1.67
[PDF]Actions Speak Louder than Answers: Privileged-Context Self-Distillation for VLM Safety▼1.2k3.00
[PDF]Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring▲3.0k2.33
[PDF]Directing Safety Signals to the Appropriate Neurons: Multilingual Safety Alignment through Selective Neuron Masking▲9.2k2.67
[PDF]Replication Is Not Specificity: Negative Controls for Representation-Based Reward-Hacking Detection▼1361.33
[PDF]Beyond Positive Bias: Customizing and Correcting Generative Robot Policies via Negative Guidance▼4.3k2.00
[PDF]DeShortcut-Align: Decoupling Spurious Shortcuts for Robust Safety Alignment in Large Reasoning Models▲5103.00
[PDF]Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks▲3.0k2.33
Withdrawn or desk rejected (231)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