LLM-based security code review is vulnerable to framing bias, with a novel iterative refinement attack achieving 100% success in reintroducing vulnerabilities across real projects.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SE 2years
2026 2representative citing papers
Agentic LLMs remain robust to renaming and insertion but degrade on composed transformations and deeper obfuscation in CTF tasks, enabled by a new Evolve-CTF tool for generating equivalent challenge families.
citing papers explorer
-
Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review
LLM-based security code review is vulnerable to framing bias, with a novel iterative refinement attack achieving 100% success in reintroducing vulnerabilities across real projects.
-
Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations
Agentic LLMs remain robust to renaming and insertion but degrade on composed transformations and deeper obfuscation in CTF tasks, enabled by a new Evolve-CTF tool for generating equivalent challenge families.