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

Statically Discover Cross-Entry Use-After-Free Vulnerabilities in the Linux Kernel

Hang Zhang (Indiana University Bloomington), Jangha Kim (The Affiliated Institute of ETRI, ROK), Chuhong Yuan (Georgia Institute of Technology), Zhiyun Qian (University of California, Riverside), Taesoo Kim (Georgia Institute of Technology)

Read More

Blindfold: Confidential Memory Management by Untrusted Operating System

Caihua Li (Yale University), Seung-seob Lee (Yale University), Lin Zhong (Yale University)

Read More

Rethink Custom Transformers for Binary Analysis

Heng Yin, Professor, Department of Computer Science and Engineering, University of California, Riverside

Read More

MALintent: Coverage Guided Intent Fuzzing Framework for Android

Ammar Askar (Georgia Institute of Technology), Fabian Fleischer (Georgia Institute of Technology), Christopher Kruegel (University of California, Santa Barbara), Giovanni Vigna (University of California, Santa Barbara), Taesoo Kim (Georgia Institute of Technology)

Read More