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
100 results for “keyword:"agent security"” in ICLR 2027. 22 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Human Before the Loop: Constraining the Action Space Improves Security, Reliability, and Capability in AI Agents▼4.3k2.00
[PDF]Compositional Permission Flow Verification for Multi-Agent LLM Systems with Adaptive Security Consolidation▼1361.33
[PDF]The Refraction Gap: How Optical Context Compression Inadvertently Bypasses Safety Alignment▲3.0k2.33
[PDF]Authorization and Endorsement Forgery in Multi-Agent Evaluation: Propagation and Defense▼4.3k2.00
[PDF]Tracing Paths to Risk: Automated Safety Evaluation for Tool-used Agents via Risk-Path Exploration▼4.3k2.00
[PDF]Can Agents Safely Expand Their Capabilities? An Empirical Study of Trust Decisions in Autonomous Capability Discovery▲3.0k2.33
[PDF]AsymStego: Exploiting Information Asymmetry to Bypass Content-Level Auditing in LLM Agents▲3952.67
[PDF]From Search Success to Deployment Reliability: Rethinking Automated Red Teaming for Indirect Prompt Injection▼4.3k2.00
[PDF]Survival of the Flawed: How Agent Harness Evolution Inherit, Amplify, and Generalize Adversarial Trajectories▼4.3k2.00
[PDF]Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents▲3.9k1.67
[PDF]Autonomous Red Teaming for Utility-Preserving Indirect Prompt Injection via Fine-Grained Diagnosis▼1.2k1.67
Withdrawn or desk rejected (22)
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00
[PDF]Adaptive-Attack Robustness of Prompt-Injection Detectors for Agentic Tool-Response ContentDesk rejected
[PDF]Harmless Here, Harmful There: Safety and Privacy Inversion of Agent Memory Across Model MigrationWithdrawn1.33
[PDF]HelpInject: Reframing Adversarial Goals as Helpful Solutions for Indirect Prompt Injection in LLM AgentsWithdrawn1.67