activity
20232026
most citedSAFE: Advancing Large Language Models in Leveraging Semantic and Syntactic Relationships for Software Vulnerability Detection

2 citations · 5 across the 9 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CR2026

When External Threats Become User Context: Tricking Agents into Accepting Malicious Information

Fengchao Chen, Tingmin Wu, Van Nguyen +3

Autonomous LLM agents receive task goals through user requests, but these requests may also relay untrusted external information. We study source relocation, where an externally av…