Presents TRUST-Bench benchmark for hidden-trigger tool compromises in LLM agents and VISTA-Guard framework for trajectory-aware risk scoring of final actions under untrusted feedback.
Edward Suh
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CR 3years
2026 3representative citing papers
Stage-level tracking of prompt injection reveals that write-node placement and model-specific behaviors determine attack outcomes more than initial exposure in LLM pipelines.
LLM agent security is reframed as an agent-human interaction issue, supported by a survey showing industry preference for human-centric mechanisms over academic favorites and proposing a new research agenda.
citing papers explorer
-
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback
Presents TRUST-Bench benchmark for hidden-trigger tool compromises in LLM agents and VISTA-Guard framework for trajectory-aware risk scoring of final actions under untrusted feedback.
-
Reframing LLM Agent Security as an Agent-Human Interaction Problem
LLM agent security is reframed as an agent-human interaction issue, supported by a survey showing industry preference for human-centric mechanisms over academic favorites and proposing a new research agenda.