5 papers
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…
Text Adversarial Attacks with Dynamic Outputs
Wenqiang Wang, Siyuan Liang, Xiao Yan +1
Text adversarial attack methods are typically designed for static scenarios with fixed numbers of output labels and a predefined label space, relying on extensive querying of the v…
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…
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…
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…