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

Rethinking Trust in Forge-Based Git Security

Aditya Sirish A Yelgundhalli (New York University), Patrick Zielinski (New York University), Reza Curtmola (New Jersey Institute of Technology), Justin Cappos (New York University)

Read More

OrbID: Identifying Orbcomm Satellite RF Fingerprints

Cédric Solenthaler (ETH Zurich), Joshua Smailes (University of Oxford), Martin Strohmeier (armasuisse Science & Technology)

Read More

Rondo: Scalable and Reconfiguration-Friendly Randomness Beacon

Xuanji Meng (Tsinghua University), Xiao Sui (Shandong University), Zhaoxin Yang (Tsinghua University), Kang Rong (Blockchain Platform Division,Ant Group), Wenbo Xu (Blockchain Platform Division,Ant Group), Shenglong Chen (Blockchain Platform Division,Ant Group), Ying Yan (Blockchain Platform Division,Ant Group), Sisi Duan (Tsinghua University)

Read More