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

One Engine To Serve 'em All: Inferring Taint Rules...

Zheng Leong Chua (National University of Singapore), Yanhao Wang (TCA/SKLCS, Institute of Software, Chinese Academy of Sciences), Teodora Baluta (National University of Singapore), Prateek Saxena (National University of Singapore), Zhenkai Liang (National University of Singapore), Purui Su (TCA/SKLCS, Institute of Software, Chinese Academy of Sciences)

Read More

NIC: Detecting Adversarial Samples with Neural Network Invariant Checking

Shiqing Ma (Purdue University), Yingqi Liu (Purdue University), Guanhong Tao (Purdue University), Wen-Chuan Lee (Purdue University), Xiangyu Zhang (Purdue University)

Read More

Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic...

Lea Schönherr (Ruhr University Bochum), Katharina Kohls (Ruhr University Bochum), Steffen Zeiler (Ruhr University Bochum), Thorsten Holz (Ruhr University Bochum), Dorothea Kolossa (Ruhr University Bochum)

Read More

Don't Trust The Locals: Investigating the Prevalence of Persistent...

Marius Steffens (CISPA Helmholtz Center for Information Security), Christian Rossow (CISPA Helmholtz Center for Information Security), Martin Johns (TU Braunschweig), Ben Stock (CISPA Helmholtz Center for Information Security)

Read More