Hanlei Zhang (Zhejiang University), Yijie Bai (Zhejiang University), Yanjiao Chen (Zhejiang University), Zhongming Ma (Zhejiang University), Wenyuan Xu (Zhejiang University)

Backdoor attacks are an essential risk to deep learning model sharing. Fundamentally, backdoored models are different from benign models considering latent separability, i.e., distinguishable differences in model latent representations. However, existing methods quantify latent separability by clustering latent representations or computing distances between latent representations, which are easy to be compromised by adaptive attacks. In this paper, we propose BARBIE, a backdoor detection approach that can pinpoint latent separability under adaptive backdoor attacks. To achieve this goal, we propose a new latent separability metric, named relative competition score (RCS), by characterizing the dominance of latent representations over model output, which is robust against various backdoor attacks and is hard to compromise. Without the need to access any benign or backdoored sample, we invert two sets of latent representations of each label, reflecting the normal latent representations of benign models and intensifying the abnormal ones of backdoored models, to calculate RCS. We compute a series of RCS-based indicators to comprehensively reflect the differences between backdoored models and benign models. We validate the effectiveness of BARBIE on more than 10,000 models on 4 datasets against 14 types of backdoor attacks, including the adaptive attacks against latent separability. Compared with 7 baselines, BARBIE improves the average true positive rate by 17.05% against source-agnostic attacks, 27.72% against source-specific attacks, 43.17% against sample-specific attacks and 11.48% against clean-label attacks. BARBIE also maintains lower false positive rates than baselines. The source code is available at: https://github.com/Forliqr/BARBIE.

View More Papers

Non-intrusive and Unconstrained Keystroke Inference in VR Platforms via...

Tao Ni (City University of Hong Kong), Yuefeng Du (City University of Hong Kong), Qingchuan Zhao (City University of Hong Kong), Cong Wang (City University of Hong Kong)

Read More

Evaluating LLMs Towards Automated Assessment of Privacy Policy Understandability

Keika Mori (Deloitte Tohmatsu Cyber LLC, Waseda University), Daiki Ito (Deloitte Tohmatsu Cyber LLC), Takumi Fukunaga (Deloitte Tohmatsu Cyber LLC), Takuya Watanabe (Deloitte Tohmatsu Cyber LLC), Yuta Takata (Deloitte Tohmatsu Cyber LLC), Masaki Kamizono (Deloitte Tohmatsu Cyber LLC), Tatsuya Mori (Waseda University, NICT, RIKEN AIP)

Read More

Careful About What App Promotion Ads Recommend! Detecting and...

Shang Ma (University of Notre Dame), Chaoran Chen (University of Notre Dame), Shao Yang (Case Western Reserve University), Shifu Hou (University of Notre Dame), Toby Jia-Jun Li (University of Notre Dame), Xusheng Xiao (Arizona State University), Tao Xie (Peking University), Yanfang Ye (University of Notre Dame)

Read More

Attributing Open-Source Contributions is Critical but Difficult: A Systematic...

Jan-Ulrich Holtgrave (CISPA Helmholtz Center for Information Security), Kay Friedrich (CISPA Helmholtz Center for Information Security), Fabian Fischer (CISPA Helmholtz Center for Information Security), Nicolas Huaman (Leibniz University Hannover), Niklas Busch (CISPA Helmholtz Center for Information Security), Jan H. Klemmer (CISPA Helmholtz Center for Information Security), Marcel Fourné (Paderborn University), Oliver Wiese (CISPA Helmholtz Center…

Read More