2 papers
cs.CR2026
MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
Georgios Syros, Evan Rose, Brian Grinstead +4
Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behal…
cs.CR2026
Syntax- and Compilation-Preserving Evasion of LLM Vulnerability Detectors
Luze Sun, Alina Oprea, Eric Wong
LLM-based vulnerability detectors are increasingly deployed in CI/CD security gating, yet their resilience to evasion under syntax- and compilation-preserving edits remains poorly…