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

Poster: Securing IoT Edge Devices: Applying NIST IR 8259A...

Rahul Choutapally, Konika Reddy Saddikuti, Solomon Berhe (University of the Pacific)

Read More

MOBIDOJO: A Virtual Security Combat Platform for 5G Cellular...

Hyunwoo Lee (Ohio State University), Haohuang Wen (Ohio State University), Phillip Porras (SRI), Vinod Yegneswaran (SRI), Ashish Gehani (SRI), Prakhar Sharma (SRI), Zhiqiang Lin (Ohio State University)

Read More

CCTAG: Configurable and Combinable Tagged Architecture

Zhanpeng Liu (Peking University), Yi Rong (Tsinghua University), Chenyang Li (Peking University), Wende Tan (Tsinghua University), Yuan Li (Zhongguancun Laboratory), Xinhui Han (Peking University), Songtao Yang (Zhongguancun Laboratory), Chao Zhang (Tsinghua University)

Read More

ReDAN: An Empirical Study on Remote DoS Attacks against...

Xuewei Feng (Tsinghua University), Yuxiang Yang (Tsinghua University), Qi Li (Tsinghua University), Xingxiang Zhan (Zhongguancun Lab), Kun Sun (George Mason University), Ziqiang Wang (Southeast University), Ao Wang (Southeast University), Ganqiu Du (China Software Testing Center), Ke Xu (Tsinghua University)

Read More