Shuo Shao (Zhejiang University), Yiming Li (Zhejiang University), Hongwei Yao (Zhejiang University), Yiling He (Zhejiang University), Zhan Qin (Zhejiang University), Kui Ren (Zhejiang University)

Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by examining whether it has particular properties `inherited' from their released models. Currently, backdoor-based model watermarks are the primary and cutting-edge methods to implant such properties in the released models. However, backdoor-based methods have two fatal drawbacks, including emph{harmfulness} and emph{ambiguity}. The former indicates that they introduce maliciously controllable misclassification behaviors ($i.e.$, backdoor) to the watermarked released models. The latter denotes that malicious users can easily pass the verification by finding other misclassified samples, leading to ownership ambiguity.

In this paper, we argue that both limitations stem from the 'zero-bit' nature of existing watermarking schemes, where they exploit the status ($i.e.$, misclassified) of predictions for verification. Motivated by this understanding, we design a new watermarking paradigm, $i.e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions. Specifically, EaaW embeds a `multi-bit' watermark into the feature attribution explanation of specific trigger samples without changing the original prediction. We correspondingly design the watermark embedding and extraction algorithms inspired by explainable artificial intelligence. In particular, our approach can be used for different tasks ($e.g.$, image classification and text generation). Extensive experiments verify the effectiveness and harmlessness of our EaaW and its resistance to potential attacks.

View More Papers

GhostShot: Manipulating the Image of CCD Cameras with Electromagnetic...

Yanze Ren (Zhejiang University), Qinhong Jiang (Zhejiang University), Chen Yan (Zhejiang University), Xiaoyu Ji (Zhejiang University), Wenyuan Xu (Zhejiang University)

Read More

ERW-Radar: An Adaptive Detection System against Evasive Ransomware by...

Lingbo Zhao (Institute of Information Engineering, Chinese Academy of Sciences), Yuhui Zhang (Institute of Information Engineering, Chinese Academy of Sciences), Zhilu Wang (Institute of Information Engineering, Chinese Academy of Sciences), Fengkai Yuan (Institute of Information Engineering, CAS), Rui Hou (Institute of Information Engineering, Chinese Academy of Sciences)

Read More

SecuWear: Secure Data Sharing Between Wearable Devices

Sujin Han (KAIST) Diana A. Vasile (Nokia Bell Labs), Fahim Kawsar (Nokia Bell Labs, University of Glasgow), Chulhong Min (Nokia Bell Labs)

Read More

Do We Really Need to Design New Byzantine-robust Aggregation...

Minghong Fang (University of Louisville), Seyedsina Nabavirazavi (Florida International University), Zhuqing Liu (University of North Texas), Wei Sun (Wichita State University), Sundararaja Iyengar (Florida International University), Haibo Yang (Rochester Institute of Technology)

Read More