【扩展版】反思深度神经网络所有权验证:嵌入护照击败歧义攻击
[Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks
摘要:
随着大量的时间、资源和人力(团队)努力投入到探索和开发成功的深度神经网络(DNN)中,迫切需要保护这些发明免受非法复制、重新分发或滥用,而不尊重合法所有者的知识产权。根据这方面的最新进展,我们研究了一些基于水印的DNN所有权验证方法,面对歧义攻击,其目的是通过伪造伪造水印来质疑所有权验证。结果表明,模糊攻击对现有的DNN水印方法构成严重威胁。作为对上述漏洞的补救,本文提出了新的基于护照的DNN所有权验证方案,该方案对网络修改具有鲁棒性,并且能够抵御歧义攻击。嵌入数字护照的要点是设计和训练DNN模型,使得原始任务的DNN推理性能将由于伪造护照而显著恶化。换句话说,真正的护照不仅通过寻找预定义的签名来验证,而且还通过不屈的DNN模型推理性能来重申。大量的实验结果证明了所提出的基于护照的DNN所有权验证方案的有效性。代码和模型可在https://github.com/kamwoh/DeepIPR上获得
英文摘要:
With substantial amount of time, resources and human (team) efforts invested to explore and develop successful deep neural networks (DNN), there emerges an urgent need to protect these inventions from being illegally copied, redistributed, or abused without respecting the intellectual properties of legitimate owners. Following recent progresses along this line, we investigate a number of watermark-based DNN ownership verification methods in the face of ambiguity attacks, which aim to cast doubts on the ownership verification by forging counterfeit watermarks. It is shown that ambiguity attacks pose serious threats to existing DNN watermarking methods. As remedies to the above-mentioned loophole, this paper proposes novel passport-based DNN ownership verification schemes which are both robust to network modifications and resilient to ambiguity attacks. The gist of embedding digital passports is to design and train DNN models in a way such that, the DNN inference performance of an original task will be significantly deteriorated due to forged passports. In other words, genuine passports are not only verified by looking for the predefined signatures, but also reasserted by the unyielding DNN model inference performances. Extensive experimental results justify the effectiveness of the proposed passport-based DNN ownership verification schemes. Code and models are available at https://github.com/kamwoh/DeepIPR
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。