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

SOC Service Areas: Identification, Prioritization, and Implementation

Christopher Rodman, Breanna Kraus, Justin Novak (SEI/CERT)

Read More

Proof of Backhaul: Trustfree Measurement of Broadband Bandwidth

Peiyao Sheng (Kaleidoscope Blockchain Inc.), Nikita Yadav (Indian Institute of Science), Vishal Sevani (Kaleidoscope Blockchain Inc.), Arun Babu (Kaleidoscope Blockchain Inc.), Anand Svr (Kaleidoscope Blockchain Inc.), Himanshu Tyagi (Indian Institute of Science), Pramod Viswanath (Kaleidoscope Blockchain Inc.)

Read More

UniID: Spoofing Face Authentication System by Universal Identity

Zhihao Wu (Zhejiang University), Yushi Cheng (Zhejiang University), Shibo Zhang (Zhejiang University), Xiaoyu Ji (Zhejiang University), Wenyuan Xu (Zhejing University)

Read More

WIP: Adversarial Object-Evasion Attack Detection in Autonomous Driving Contexts:...

Rao Li (The Pennsylvania State University), Shih-Chieh Dai (Pennsylvania State University), Aiping Xiong (Penn State University)

Read More