collaborators

6 papers

cs.CL2026

EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation

Xinda Wang, Zhengxu Hou, Yangshijie Zhang +6

Although the effectiveness of Large Language Models (LLMs) as judges (LLM-as-a-judge) has been validated, their performance remains limited in open-ended tasks, particularly in sto…

cs.CL2025

Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent

Yangshijie Zhang, Xinda Wang, Jialin Liu +3

With social media growth, users employ stylistic fonts and font-like emoji to express individuality, creating visually appealing text that remains human-readable. However, these fo…

cs.CR2025

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries

Wenqiang Wang, Yan Xiao, Hao Lin +2

Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attack…

cs.CL2025

No Query, No Access

Wenqiang Wang, Siyuan Liang, Yangshijie Zhang +3

Textual adversarial attacks mislead NLP models, including Large Language Models (LLMs), by subtly modifying text. While effective, existing attacks often require knowledge of the v…

cs.CV2025

Incomplete In-context Learning

Wenqiang Wang, Yangshijie Zhang

Large vision language models (LVLMs) achieve remarkable performance through Vision In-context Learning (VICL), a process that depends significantly on demonstrations retrieved from…

cs.AI2025

Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences

Yangshijie Zhang

Deep neural networks (DNNs) have achieved remarkable success in the field of natural language processing (NLP), leading to widely recognized applications such as ChatGPT. However,…