Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems

arXiv:2606.20470 · cs.CR, cs.AI · Submitted 2026-06-18 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-06-18

Updated: 2026-09-30

Code: https://github.com/llm-attacks/llm-attacks

Terminology

• Verification — 26× in this paper · explained in 2 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• LLM judge — 8× in this paper · explained in 2 episodes
• Agentic AI — 7× in this paper · explained in 1 episode
• Alignment — 6× in this paper · explained in 1 episode
• Agentic AI systems — 5× in this paper · explained in 1 episode
• Abstraction — 3× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• LLM-as-a-Judge — 3× in this paper · explained in 3 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Conference on Secure and Trustworthy Machine Learning — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Fingerprinting — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Deliberative Alignment: Reasoning Enables Safer Language Models
• Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
• "To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios
• Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks
• GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

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