Wanlun Ma (Swinburne University of Technology), Derui Wang (CSIRO’s Data61), Ruoxi Sun (The University of Adelaide & CSIRO's Data61), Minhui Xue (CSIRO's Data61), Sheng Wen (Swinburne University of Technology), Yang Xiang (Digital Research & Innovation Capability Platform, Swinburne University of Technology)

Deep Neural Networks (DNNs) are susceptible to backdoor attacks during training. The model corrupted in this way functions normally, but when triggered by certain patterns in the input, produces a predefined target label. Existing defenses usually rely on the assumption of the universal backdoor setting in which poisoned samples share the same uniform trigger. However, recent advanced backdoor attacks show that this assumption is no longer valid in dynamic backdoors where the triggers vary from input to input, thereby defeating the existing defenses.

In this work, we propose a novel technique, Beatrix (backdoor detection via Gram matrix). Beatrix utilizes Gram matrix to capture not only the feature correlations but also the appropriately high-order information of the representations. By learning class-conditional statistics from activation patterns of normal samples, Beatrix can identify poisoned samples by capturing the anomalies in activation patterns. To further improve the performance in identifying target labels, Beatrix leverages kernel-based testing without making any prior assumptions on representation distribution. We demonstrate the effectiveness of our method through extensive evaluation and comparison with state-of-the-art defensive techniques. The experimental results show that our approach achieves an F1 score of 91.1% in detecting dynamic backdoors, while the state of the art can only reach 36.9%.

View More Papers

Understanding MPU Usage in Microcontroller-based Systems in the Wild

Wei Zhou, Zhouqi Jiang (School of Cyber Science and Engineering, Huazhong University of Science and Technology), Le Guan (School of Computing, University of Georgia)

Read More

Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks...

Hadi Abdullah (Visa Research), Aditya Karlekar (University of Florida), Saurabh Prasad (University of Florida), Muhammad Sajidur Rahman (University of Florida), Logan Blue (University of Florida), Luke A. Bauer (University of Florida), Vincent Bindschaedler (University of Florida), Patrick Traynor (University of Florida)

Read More

RCABench: Open Benchmarking Platform for Root Cause Analysis

Keisuke Nishimura, Yuichi Sugiyama, Yuki Koike, Masaya Motoda, Tomoya Kitagawa, Toshiki Takatera, Yuma Kurogome (Ricerca Security, Inc.)

Read More

Reminding Drivers of the Stalking Vehicles on the Road

Wei Sun, Kannan Srinivsan (The Ohio State University)

Read More