Showing 2026Show all
2 papers · 1 filter
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…
cs.CR2026
Exploring and Developing a Pre-Model Safeguard with Draft Models
Hongyu Cai, Arjun Arunasalam, Yiming Liang +2
Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the sa…