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
representative citing papers
PrivacyMotiv generates LLM-created speculative personas and traceable journey stories to raise UX designers' empathy and motivation for privacy, yielding 59% more privacy issues found and 70% more redesign ideas in a study of 16 professionals.
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.
-
PrivacyMotiv: Speculative Persona Journeys for Empathic and Motivating Privacy Reviews in UX Design
PrivacyMotiv generates LLM-created speculative personas and traceable journey stories to raise UX designers' empathy and motivation for privacy, yielding 59% more privacy issues found and 70% more redesign ideas in a study of 16 professionals.