SemAder: Evading LLM-Based Binary Code Analysis via Structure-Semantics Joint Induction
Summary
Researchers discovered that SemAder, a technique that manipulates both the structure and meaning of binary code (compiled programs), can fool LLM-based binary code analysis tools into missing security problems. The study shows that by carefully modifying how code is organized and what it semantically does, attackers can evade detection systems that use large language models to analyze compiled programs for vulnerabilities.
Classification
Related Issues
Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
Defending Against Patch-Based and Texture-Based Adversarial Attacks With Spectral Decomposition
Original source: https://dl.acm.org/doi/abs/10.1145/3818619?ai=2p1&mi=hx017f&af=R
First tracked: July 1, 2026 at 08:01 AM
Classified by LLM (prompt v3) · confidence: 85%