InfoResearchPreprintLLM-specific
ATrust: Adaptive Trust Boundary Expansion for Securing LLM Agents
- Published
- Record updated
Summary
ATrust is a defense for LLM agents that expands the trust boundary during runtime, starting from the user query as the root trust anchor and admitting task-essential external observations as new anchors. Evaluated on AgentDojo and AgentDyn with GPT-4o as the engine model, it reduces the attack success rate on AgentDyn from 37.80% to 4.37% while improving utility by 10.00%, outperforming AuthGraph by 12.33%.
Related items
- InfoChatGPT will now make you animated GIFsSame vendor · The Verge (AI)
- MediumResearchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak ToolkitSame vendor · The Hacker News
- InfoForrester gave Endor Labs the highest score possible in seven criteria, including innovation, AI application flaws, AI SCA, and AI coding toolchain. | Endor LabsSame vendor · Endor Labs Blog
- InfoUber only fulfilled 4 rides from AI agents last quarterSame vendor · The Verge (AI)
- InfoSam Altman addresses RAM comments: People should ‘put as much as they want in their computers’Same vendor · The Verge (AI)