Abstract: In this work, we introduce a novel large language model (LLM)-based masking mutation operator for Genetic Improvement (GI), which leverages code completion capabilities of large language ...

A new font-rendering attack causes AI assistants to miss malicious commands shown on webpages by hiding them in seemingly harmless HTML.

Abstract: As the complexity and volume of software development continue to grow, the need for efficient and thorough code review processes becomes increasingly critical. This paper explores the ...

Discover how AI tools like Claude Code revolutionize software development by taking over tedious coding tasks, allowing ...

Hidden instructions in content can subtly bias AI, and our scenario shows how prompt injection works, highlighting the need for oversight and a structured response playbook.