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

On-demand RFID: Improving Privacy, Security, and User Trust in...

Youngwook Do (JPMorganChase and Georgia Institute of Technology), Tingyu Cheng (Georgia Institute of Technology and University of Notre Dame), Yuxi Wu (Georgia Institute of Technology and Northeastern University), HyunJoo Oh(Georgia Institute of Technology), Daniel J. Wilson (Northeastern University), Gregory D. Abowd (Northeastern University), Sauvik Das (Carnegie Mellon University)

Read More

Feedback-Guided API Fuzzing of 5G Network

Tianchang Yang (Pennsylvania State University), Sathiyajith K S (Pennsylvania State University), Ashwin Senthil Arumugam (Pennsylvania State University), Syed Rafiul Hussain (Pennsylvania State University)

Read More

Evaluating the Strength and Availability of Multilingual Passphrase Authentication

Chi-en Amy Tai (University of Waterloo), Urs Hengartner (University of Waterloo), Alexander Wong (University of Waterloo)

Read More

Inspecting Compiler Optimizations on Mixed Boolean Arithmetic Obfuscation

Rachael Little, Dongpeng Xu (University of New Hampshire)

Read More