Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic environments, especially under attack? To investigate, we...

Attacker'S Noise Can Manipulate Your Audio-Based LLM in the Real World

This paper investigates the real-world vulnerabilities of audio-based large language models ALLMs, such as Qwen2-Audio. We first demonstrate that an adversary can craft stealthy audio perturbations to manipulate ALLMs into exhibiting specific targeted behaviors, such as eliciting responses to...

Explainer-Guided Targeted Adversarial Attacks against Binary Code Similarity Detection Models

Binary code similarity detection BCSD serves as a fundamental technique for various software engineering tasks, e.g., vulnerability detection and classification. Attacks against such models have therefore drawn extensive attention, aiming at misleading the models to generate erroneous predictions...