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

Robust Performance Metrics for Authentication Systems

Shridatt Sugrim (Rutgers University), Can Liu (Rutgers University), Meghan McLean (Rutgers University), Janne Lindqvist (Rutgers University)

Read More

Profit: Detecting and Quantifying Side Channels in Networked Applications

Nicolás Rosner (University of California, Santa Barbara), Ismet Burak Kadron (University of California, Santa Barbara), Lucas Bang (Harvey Mudd College), Tevfik Bultan (University of California, Santa Barbara)

Read More

Anonymous Multi-Hop Locks for Blockchain Scalability and Interoperability

Giulio Malavolta (Friedrich-Alexander University Erlangen-Nürnberg), Pedro Moreno Sanchez (TU Wien), Clara Schneidewind (TU Wien), Aniket Kate (Purdue University), Matteo Maffei (TU Wien)

Read More

NoDoze: Combatting Threat Alert Fatigue with Automated Provenance Triage

Wajih Ul Hassan (NEC Laboratories America, Inc.; University of Illinois at Urbana–Champaign), Shengjian Guo (Virginia Tech), Ding Li (NEC Laboratories America, Inc.), Zhengzhang Chen (NEC Laboratories America, Inc.), Kangkook Jee (NEC Laboratories America, Inc.), Zhichun Li (NEC Laboratories America, Inc.), Adam Bates (University of Illinois at Urbana–Champaign)

Read More