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
29 results for “keyword:"cybersecurity"” in ICLR 2027. 8 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation▼1.2k1.67
[PDF]RedHerring: Verification Effort as a Defense Surface Against LLM Agents in Vulnerability Discovery▼5.8k2.33
[PDF]The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark▲153.33
[PDF]Adaptive Retrieval and Verification: A Shared Agentic Controller for Cybersecurity RAG and GraphRAG▼1351.33
[PDF]CVE-Bench Hard: Rigorous Evaluation of AI Agents for Identifying and Exploiting Complex Web Application Vulnerabilities▼4.5k2.67
[PDF]SysRepair-Bench: Measuring Whether Agents Can Fix a Vulnerability Without Breaking the Service▼4.5k2.67
[PDF]ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?▼4.3k2.00
[PDF]The Hidden Fragility of AI Safety: How Guardrails Can Weaken Cyber and Biological Resilience▼1.2k1.67
[PDF]Where to Perturb? Perturbation Allocation in Representation-Space Augmentation for Sparse Event Detection▼5.8k2.33
[PDF]CyberPersistBench: Evaluating LLM-Based Cyber Attackers on Installation and Persistence▼1.2k3.00
[PDF]Discovery or Memorization? A Faithful Benchmark for Real-World Business-Logic Vulnerability Discovery▲5103.00
[PDF]Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks▲9.2k2.67
Withdrawn or desk rejected (8)
[PDF]Behavior-Based Insider Threat Detection Using Machine Learning: A Comparative Study of Isolation Forest, Random Forest, and XGBoostDesk rejected
[PDF]Learning representations of operating system level data and designing interpretable AI for defensive cybersecurityWithdrawn1.00
[PDF]CyLawBench: Evaluating LLM Agents' Compliance with Cyber Law under Dynamic Adversarial InductionDesk rejected1.50