Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents
Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed +2
Browser-use agents often carry information in their context as they move between websites. While it may be necessary for task completion, it also creates a privacy risk, especially…
cs.CR2026
Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
Asif Shahriar, Hongyu Cai, Hadjer Benkraouda +2
Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection. Recent work has shown that LLMs are susceptible to the same cog…