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

Towards Automated Regulation Analysis for Effective Privacy Compliance

Sunil Manandhar (IBM T.J. Watson Research Center), Kapil Singh (IBM T.J. Watson Research Center), Adwait Nadkarni (William & Mary)

Read More

LDR: Secure and Efficient Linux Driver Runtime for Embedded...

Huaiyu Yan (Southeast University), Zhen Ling (Southeast University), Haobo Li (Southeast University), Lan Luo (Anhui University of Technology), Xinhui Shao (Southeast University), Kai Dong (Southeast University), Ping Jiang (Southeast University), Ming Yang (Southeast University), Junzhou Luo (Southeast University, Nanjing, P.R. China), Xinwen Fu (University of Massachusetts Lowell)

Read More

Content Censorship in the InterPlanetary File System

Srivatsan Sridhar (Stanford University), Onur Ascigil (Lancaster University), Navin Keizer (University College London), François Genon (UCLouvain), Sébastien Pierre (UCLouvain), Yiannis Psaras (Protocol Labs), Etienne Riviere (UCLouvain), Michał Król (City, University of London)

Read More

Reverse Engineering of Multiplexed CAN Frames (Long)

Alessio Buscemi, Thomas Engel (SnT, University of Luxembourg), Kang G. Shin (The University of Michigan)

Read More