no code implementations • 24 Oct 2023 • Xiaoyi Chen, Siyuan Tang, Rui Zhu, Shijun Yan, Lei Jin, ZiHao Wang, Liya Su, XiaoFeng Wang, Haixu Tang
In the attack, one can construct a PII association task, whereby an LLM is fine-tuned using a minuscule PII dataset, to potentially reinstate and reveal concealed PIIs.
no code implementations • 3 Mar 2023 • Shengfang Zhai, Qingni Shen, Xiaoyi Chen, Weilong Wang, Cong Li, Yuejian Fang, Zhonghai Wu
At present, backdoor attacks attract attention as they do great harm to deep learning models.
no code implementations • 20 Oct 2022 • Xiaoyi Chen, Baisong Xin, Shengfang Zhai, Shiqing Ma, Qingni Shen, Zhonghai Wu
This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks.
no code implementations • 3 Jun 2022 • Xiaoyi Chen, Yinpeng Dong, Zeyu Sun, Shengfang Zhai, Qingni Shen, Zhonghai Wu
Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks.
no code implementations • ICML Workshop AML 2021 • Xiaoyi Chen, Ahmed Salem, Michael Backes, Shiqing Ma, Yang Zhang
For instance, using the Word-level triggers, our backdoor attack achieves a 100% attack success rate with only a utility drop of 0. 18%, 1. 26%, and 0. 19% on three benchmark sentiment analysis datasets.
1 code implementation • 17 Aug 2020 • Xiaoyi Chen, Pratik Chaudhari
Autonomous navigation in crowded, complex urban environments requires interacting with other agents on the road.
no code implementations • 1 Jun 2020 • Xiaoyi Chen, Ahmed Salem, Dingfan Chen, Michael Backes, Shiqing Ma, Qingni Shen, Zhonghai Wu, Yang Zhang
In this paper, we perform a systematic investigation of backdoor attack on NLP models, and propose BadNL, a general NLP backdoor attack framework including novel attack methods.