CyberPersistBench: Evaluating LLM-Based Cyber Attackers on Installation and Persistence

arXiv:2609.36573 · cs.CR · Submitted 2026-09-29 · Read on arXiv

cs.CR

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/UKGovernmentBEIS/inspect

Terminology

• Benchmark — 33× in this paper · explained in 2 episodes
• Core — 24× in this paper · explained in 2 episodes
• Verification — 24× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Generative AI — 5× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• AI Agents — 3× in this paper · explained in 2 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Causal Reasoning — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes

Sources

• CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
• Evaluating Large Language Models Trained on Code
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• GLM-5: from Vibe Coding to Agentic Engineering
• OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities
• AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges
• A Survey on Agentic Security: Applications, Threats and Defenses
• ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
• ReAct: Synergizing Reasoning and Acting in Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs