Timezone: »

Watermarking for Out-of-distribution Detection
Qizhou Wang · Feng Liu · Yonggang Zhang · Jing Zhang · Chen Gong · Tongliang Liu · Bo Han

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #202

Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models. However, existing methods largely ignore the reprogramming property of deep models and thus may not fully unleash their intrinsic strength: without modifying parameters of a well-trained deep model, we can reprogram this model for a new purpose via data-level manipulation (e.g., adding a specific feature perturbation). This property motivates us to reprogram a classification model to excel at OOD detection (a new task), and thus we propose a general methodology named watermarking in this paper. Specifically, we learn a unified pattern that is superimposed onto features of original data, and the model's detection capability is largely boosted after watermarking. Extensive experiments verify the effectiveness of watermarking, demonstrating the significance of the reprogramming property of deep models in OOD detection.

Author Information

Qizhou Wang (Hong Kong Baptist University)
Feng Liu (University of Melbourne)
Yonggang Zhang (Hong Kong Baptist University)
Jing Zhang (The University of Sydney)
Chen Gong (Nanjing University of Science and Technology)
Tongliang Liu (The University of Sydney)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors