ATrust adaptively expands trust boundary to secure LLM agents
ATrust reduces AgentDyn attack success rate from 37.80% to 4.37% while boosting utility by 10% with GPT-4o.
Stories per day · 30 days
1 RSS
5 stories, newest first · one card per story
Stories tagged #trust-boundary
ToFu: Exploiting and Fuzzing the LLM-Orchestrator-Tool Trust Boundary
ToFu fuzzing found verified semantic bugs in 343 LLM tools across 118 MCP servers.
LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense
LTBD uses learnable trust delimiters to sharply reduce prompt-injection success without changing LLM weights.
Origin Is All You Need: Provenance-Aware Transformers for Structural Trust-Boundary Separation
Provenance-aware transformers use origin labels to structurally block indirect prompt injection.
Autonomy in Check: Governor-Mediated Adaptive Security at the Edge
Split-control architecture adds a deterministic governor to validate LLM and rule-based planner intents before eBPF enforcement at the edge.