5 papers
SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents
Mengyao Du, Han Fang, Haokai Ma +4
Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious i…
Less Approximates More: Harmonizing Performance and Confidence Faithfulness via Hybrid Post-Training for High-Stakes Tasks
Haokai Ma, Lee Yan Zhen, Gang Yang +3
Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause severe real-world harm, bringing the previously overlooked…
AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding
Haokai Ma, Javier Yong, Yunshan Ma +4
Cyber Threat Intelligence (CTI) reports document observations of cyber threats, synthesizing evidence about adversaries' actions and intent into actionable knowledge that informs d…
TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
Mengyao Du, Han Fang, Haokai Ma +4
Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit…
MM-AttacKG: A Multimodal Approach to Attack Graph Construction with Large Language Models
Yongheng Zhang, Xinyun Zhao, Yunshan Ma +5
Cyber Threat Intelligence (CTI) parsing aims to extract key threat information from massive data, transform it into actionable intelligence, enhance threat detection and defense ef…