2 citations · 3 across the 10 of their papers we have counts for
12 papers
How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression
Xijie Gong, Tingxu Han, Jiahao Zhang +5
Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds directly remains poorly underst…
COVER: Codec-Robust Video Watermarking with Generative Video Priors
Yuxin Cao, Hao Yang, Ziqi Ding +2
Video watermarking underpins copyright protection and provenance for generated media, yet almost every video is compressed by a codec before it is stored or shared. A codec discard…
PUFFERDOS: Efficient and Effective Attack String Generation for Regular Expression Denial of Service Vulnerabilities
Shangzhi Xu, Ziqi Ding, Xiao Cheng +5
ReDoS attacks constitute a critical class of resource-exhaustion vulnerabilities. In such attacks, adversaries exploit the pathological worst-case execution behavior of regular exp…
Membership Inference Attacks Against Video Large Language Models
Wei Song, Yuxin Cao, Ziqi Ding +3
Video large language models (VideoLLMs) are increasingly trained or instruction-tuned on large-scale video--text corpora collected from heterogeneous sources, raising an immediate…
Robust CAPTCHA Using Audio Illusions in the Era of Large Language Models: from Evaluation to Advances
Ziqi Ding, Yunfeng Wan, Wei Song +7
CAPTCHAs are widely used by websites to block bots and spam by presenting challenges that are easy for humans but difficult for automated programs to solve. To improve accessibilit…
NGCaptcha: A CAPTCHA Bridging the Past and the Future
Ziqi Ding, Shangzhi Xu, Wei Song +1
CAPTCHAs are widely employed for distinguishing humans from automated bots online. However, current vision based CAPTCHAs face escalating security risks: traditional attacks contin…
Debiasing LLMs by Masking Unfairness-Driving Attention Heads
Tingxu Han, Wei Song, Ziqi Ding +6
Large language models (LLMs) increasingly mediate decisions in domains where unfair treatment of demographic groups is unacceptable. Existing work probes when biased outputs appear…
Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models
Wei Song, Haonan Zhong, Ziqi Ding +2
The Model Context Protocol (MCP) enables large language models (LLMs) to access external resources on demand. While commonly assumed to enhance performance, how LLMs actually lever…
"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas
Junchen Ding, Penghao Jiang, Zihao Xu +4
As large language models (LLMs) increasingly mediate ethically sensitive decisions, understanding their moral reasoning processes becomes imperative. This study presents a comprehe…
A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories
Ziqi Ding, Qian Fu, Junchen Ding +3
Recent advancements in large language models (LLMs) have spurred the development of diverse AI applications from code generation and video editing to text generation; however, AI s…
IllusionCAPTCHA: A CAPTCHA based on Visual Illusion
Ziqi Ding, Gelei Deng, Yi Liu +4
CAPTCHAs have long been essential tools for protecting applications from automated bots. Initially designed as simple questions to distinguish humans from bots, they have become in…
TombRaider: Entering the Vault of History to Jailbreak Large Language Models
Junchen Ding, Jiahao Zhang, Yi Liu +3
Warning: This paper contains content that may involve potentially harmful behaviours, discussed strictly for research purposes. Jailbreak attacks can hinder the safety of Large Lan…