Timezone: »

Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks
Lixin Fan · Kam Woh Ng · Chee Seng Chan

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #98

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

Author Information

Lixin Fan (WeBank AI Lab)

Dr. Lixin Fan is a Principal Scientist affiliated with WeBank, China. His research areas of interests include machine learning & deep learning, computer vision & pattern recognition, image and video processing, 3D big data processing, data visualization & rendering, augmented and virtual reality, mobile ubiquitous and pervasive computing, and intelligent human-computer interface. Dr. Fan is the (co-)author of more than 60 international journal & conference publications. He also (co-)invented more than a hundred granted and pending patents filed in US, Europe, and China. Before joining WeBank, Dr. Fan was affiliated with Nokia Technologies and Xerox Research Center Europe (XRCE). His research work included the well-recognized bag of key-points method for image categorization.

Kam Woh Ng (University of Malaya)
Chee Seng Chan (University of Malaya)

More from the Same Authors