64 papers
Same-Origin Policy for Agentic Browsers
Xilong Wang, Xiaoxing Chen, Patrick Li +2
Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instructions. The same-origin policy (SOP) is a f…
Dynamic Malicious Skills in Agentic AI
Tianhao Chen, Zhengyuan Jiang, Yuepeng Hu +2
Skills are a key enabling component of agentic AI. While they enhance agents' capabilities, they also introduce new attack surfaces. In this work, we investigate one such attack su…
RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty
Ziqian Zhang, Xingjian Hu, Yue Huang +8
Benchmarks establish a standardized evaluation framework to systematically assess the performance of large language models (LLMs), facilitating objective comparisons and driving ad…
Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening
Mohan Zhang, Yuqi Jia, Zhen Tan +4
LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or through a few anecdotal case studie…
When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
Yuan Tian, Bing Hu, Fang Wu +3
Think-with-image reasoning is emerging as a new inference paradigm for large vision-language models, but its safety implications remain poorly understood. Existing systems already…
Fingerprinting LLMs via Prompt Injection
Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li +4
Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one mod…