1. This result constrains our machine learning domain by demonstrating that our Bayesian-optimised surrogate models for LLM agents are highly vulnerable to adaptive, multi-turn prompt injections that bypass standard static safety evaluations.
Adversarial Debate Score
48% survival rate under critique
Expert panel critique
Independent views, each critiquing the hypothesis on its own — the score rewards genuine disagreement and discounts consensus.
Supporting Research Papers
- Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, kn...
- Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences. This...
- ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adver...
- Quantifying Self-Preservation Bias in Large Language Models
Instrumental convergence predicts that sufficiently advanced AI agents will resist shutdown, yet current safety training (RLHF) may obscure this risk by teaching models to deny self-preservation motiv...
Formal Verification
Z3 checks whether the hypothesis is internally consistent, not whether it is empirically true.