Hengzhi Pei (UIUC), Jinyuan Jia (UIUC, Penn State), Wenbo Guo (UC Berkeley, Purdue University), Bo Li (UIUC), Dawn Song (UC Berkeley)

Backdoor attacks have become a major security threat for deploying machine learning models in security-critical applications. Existing research endeavors have proposed many defenses against backdoor attacks. Despite demonstrating certain empirical defense efficacy, none of these techniques could provide a formal and provable security guarantee against arbitrary attacks. As a result, they can be easily broken by strong adaptive attacks, as shown in our evaluation. In this work, we propose TextGuard, the first provable defense against backdoor attacks on text classification. In particular, TextGuard first divides the (backdoored) training data into sub-training sets, achieved by splitting each training sentence into sub-sentences. This partitioning ensures that a majority of the sub-training sets do not contain the backdoor trigger. Subsequently, a base classifier is trained from each sub-training set, and their ensemble provides the final prediction. We theoretically prove that when the length of the backdoor trigger falls within a certain threshold, TextGuard guarantees that its prediction will remain unaffected by the presence of the triggers in training and testing inputs. In our evaluation, we demonstrate the effectiveness of TextGuard on three benchmark text classification tasks, surpassing the certification accuracy of existing certified defenses against backdoor attacks. Furthermore, we propose additional strategies to enhance the empirical performance of TextGuard. Comparisons with state-of-the-art empirical defenses validate the superiority of TextGuard in countering multiple backdoor attacks. Our code and data are available at https://github.com/AI-secure/TextGuard.

View More Papers

MASTERKEY: Automated Jailbreaking of Large Language Model Chatbots

Gelei Deng (Nanyang Technological University), Yi Liu (Nanyang Technological University), Yuekang Li (University of New South Wales), Kailong Wang (Huazhong University of Science and Technology), Ying Zhang (Virginia Tech), Zefeng Li (Nanyang Technological University), Haoyu Wang (Huazhong University of Science and Technology), Tianwei Zhang (Nanyang Technological University), Yang Liu (Nanyang Technological University)

Read More

HistCAN: A real-time CAN IDS with enhanced historical traffic...

Shuguo Zhuo, Nuo Li, Kui Ren (The State Key Laboratory of Blockchain and Data Security, Zhejiang University)

Read More

Connecting the Dots in the Sky: Website Fingerprinting in...

Prabhjot Singh (University of Waterloo), Diogo Barradas (University of Waterloo), Tariq Elahi (University of Edinburgh), Noura Limam (University of Waterloo)

Read More

Large Language Model guided Protocol Fuzzing

Ruijie Meng (National University of Singapore, Singapore), Martin Mirchev (National University of Singapore), Marcel Böhme (MPI-SP, Germany and Monash University, Australia), Abhik Roychoudhury (National University of Singapore)

Read More