Adversarial Attack

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
Prompt-based adversarial attacks have become an effective means to assess the robustness of large language models (LLMs). However, …
Yujia Zheng, Tianhao Li, Haotian Huang, Tianyu Zeng, Jingyu Lu, Chuangxin Chu, Yuekai Huang, Ziyou Jiang, Qian Xiong, Yuyao Ge, Mingyang Li
Cite DOI PDF ACL Anthology arXiv x Ask KIMI
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
Paper Review | Jailbreaking LLMs by Exploiting Decoding Strategies
The authors introduce MaliciousInstruct, a new dataset; a method for evaluating response toxicity; generation exploitation, an attack that manipulates decoding hyperparameters; and generation-aware alignment, a corresponding defence.
Apr 9, 2024 7 min read Paper Review
Paper
Paper Review | Jailbreaking LLMs by Exploiting Decoding Strategies
Softmax Regression and Its Optimization
This article is part of my lecture notes from the Deep Learning Systems course taught by Tianqi Chen and J. Zico Kolter at CMU.
Mar 21, 2024 11 min read Notes
Softmax Regression and Its Optimization
Attack based on data : A novel perspective to attack sensitive points directly
Adversarial attack for time-series classification model is widely explored and many attack methods are proposed. But there is not a …
Yuyao Ge, Zhongguo Yang, Lizhe Chen, Yiming Wang, Chengyang Li
Cite Dataset PDF Page Ask KIMI
Attack based on data : A novel perspective to attack sensitive points directly