7 papers · 1 filter
SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs
Haoran Ou, Gelei Deng, Xuanye Zhang +3
As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent Skill packages task-specific in…
Mutate to Bypass: Autonomous Endpoint Evasion via Knowledge-Driven Multi-Agent Orchestration
Weifeng Yuan, Wenbo Guo, Qingyun Du +4
Public reports and open-source resources expose many EDR evasion techniques, but it remains unclear whether commercial Endpoint Detection and Response (EDR) systems can withstand t…
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
Xiaojun Jia, Jie Liao, Simeng Qin +5
Agent skills are emerging as an important attack surface in LLM-based systems. Through an empirical study of existing skill scanners, we find that current defenses primarily rely o…
MalwarePT: A Binary-Level Foundation Model for Malware Analysis
Saastha Vasan, Yuzhou Nie, Kaie Chen +6
Automated malware analysis increasingly relies on machine learning, yet most existing methods remain task-specific and depend on handcrafted features or narrowly scoped models. Rec…
To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack
Terry Yue Zhuo, Yangruibo Ding, Wenbo Guo +1
For over a decade, cybersecurity has relied on human labor scarcity to limit attackers to high-value targets manually or generic automated attacks at scale. Building sophisticated…
PromptArmor: Simple yet Effective Prompt Injection Defenses
Tianneng Shi, Kaijie Zhu, Zhun Wang +13
Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, c…
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
Kaijie Zhu, Xianjun Yang, Jindong Wang +2
Recent research has explored that LLM agents are vulnerable to indirect prompt injection (IPI) attacks, where malicious tasks embedded in tool-retrieved information can redirect th…