Jinfeng Li (Zhejiang University), Shouling Ji (Zhejiang University), Tianyu Du (Zhejiang University), Bo Li (University of California, Berkeley), Ting Wang (Lehigh University)

Deep Learning-based Text Understanding (DLTU) is the backbone technique behind various applications, including question answering, machine translation, and text classification. Despite its tremendous popularity, the security vulnerabilities of DLTU are still largely unknown, which is highly concerning given its increasing use in security-sensitive applications such as user sentiment analysis and toxic content detection. In this paper, we show that DLTU is inherently vulnerable to adversarial text attacks, in which maliciously crafted text triggers target DLTU systems and services to misbehave. Specifically, we present TextBugger, a general attack framework for generating adversarial text. In contrast of prior work, TextBugger differs in significant ways: (i) effective -- it outperforms state-of-the-art attacks in terms of attack success rate; (ii) evasive -- it preserves the utility of benign text, with 94.9% of the adversarial text correctly recognized by human readers; and (iii) efficient -- it generates adversarial text with computational complexity sub-linear to the text length. We empirically evaluate TextBugger on a set of real-world DLTU systems and services used for sentiment analysis and toxic content detection, demonstrating its effectiveness, evasiveness, and efficiency. For instance, TextBugger achieves 100% success rate on the IMDB dataset based on Amazon AWS Comprehend within 4.61 seconds and preserves 97% semantic similarity. We further discuss possible defense mechanisms to mitigate such attack and the adversary's potential countermeasures, which leads to promising directions for further research.

View More Papers

We Value Your Privacy ... Now Take Some Cookies:...

Martin Degeling (Ruhr-Universität Bochum), Christine Utz (Ruhr-Universität Bochum), Christopher Lentzsch (Ruhr-Universität Bochum), Henry Hosseini (Ruhr-Universität Bochum), Florian Schaub (University of Michigan), Thorsten Holz (Ruhr-Universität Bochum)

Read More

The Crux of Voice (In)Security: A Brain Study of...

Ajaya Neupane (University of California Riverside), Nitesh Saxena (University of Alabama at Birmingham), Leanne Hirshfield (Syracuse University), Sarah Elaine Bratt (Syracuse University)

Read More

Neuro-Symbolic Execution: Augmenting Symbolic Execution with Neural Constraints

Shiqi Shen (National University of Singapore), Shweta Shinde (National University of Singapore), Soundarya Ramesh (National University of Singapore), Abhik Roychoudhury (National University of Singapore), Prateek Saxena (National University of Singapore)

Read More

Statistical Privacy for Streaming Traffic

Xiaokuan Zhang (The Ohio State University), Jihun Hamm (The Ohio State University), Michael K. Reiter (University of North Carolina at Chapel Hill), Yinqian Zhang (The Ohio State University)

Read More