Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software
Tomer Kordonsky, Amit LeVi, Maayan Yamin +2
LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities. We study vulnerability persistence i…
cs.CR2025
Jailbreak Attack Initializations as Extractors of Compliance Directions
Amit Levi, Rom Himelstein, Yaniv Nemcovsky +2
Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space. Recent works show that initiali…