Ge Ren (Shanghai Jiao Tong University), Gaolei Li (Shanghai Jiao Tong University), Shenghong Li (Shanghai Jiao Tong University), Libo Chen (Shanghai Jiao Tong University), Kui Ren (Zhejiang University)

Well-trained deep neural network (DNN) models can be treated as commodities for commercial transactions and generate significant revenues, raising the urgent need for intellectual property (IP) protection against illegitimate reproducing. Emerging studies on IP protection often aim at inserting watermarks into DNNs, allowing owners to passively verify the ownership of target models after counterfeit models appear and commercial benefits are infringed, while active authentication against unauthorized queries of DNN-based applications is still neglected. In this paper, we propose a novel approach to protect model intellectual property, called ActiveDaemon, which incorporates a built-in access control function in DNNs to safeguard against commercial piracy. Specifically, our approach enables DNNs to predict correct outputs only for authorized users with user-specific tokens while producing poor accuracy for unauthorized users. In ActiveDaemon, the user-specific tokens are generated by a specially designed U-Net style encoder-decoder network, which can map strings and input images into numerous noise images to address identity management with large-scale user capacity. Compared to existing studies, these user-specific tokens are invisible, dynamic and more perceptually concealed, enhancing the stealthiness and reliability of model IP protection. To automatically wake up the model accuracy, we utilize the data poisoning-based training technique to unconsciously embed the ActiveDaemon into the neuron's function. We conduct experiments to compare the protection performance of ActiveDaemon with four state-of-the-art approaches over four datasets. The experimental results show that ActiveDaemon can reduce the accuracy of unauthorized queries by as much as 81% with less than a 1.4% decrease in that of authorized queries. Meanwhile, our approach can also reduce the LPIPS scores of the authorized tokens to 0.0027 on CIFAR10 and 0.0368 on ImageNet.

View More Papers

MirageFlow: A New Bandwidth Inflation Attack on Tor

Christoph Sendner (University of Würzburg), Jasper Stang (University of Würzburg), Alexandra Dmitrienko (University of Würzburg), Raveen Wijewickrama (University of Texas at San Antonio), Murtuza Jadliwala (University of Texas at San Antonio)

Read More

Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural...

Gorka Abad (Radboud University & Ikerlan Technology Research Centre), Oguzhan Ersoy (Radboud University), Stjepan Picek (Radboud University & Delft University of Technology), Aitor Urbieta (Ikerlan Technology Research Centre, Basque Research and Technology Alliance (BRTA))

Read More

TextGuard: Provable Defense against Backdoor Attacks on Text Classification

Hengzhi Pei (UIUC), Jinyuan Jia (UIUC, Penn State), Wenbo Guo (UC Berkeley, Purdue University), Bo Li (UIUC), Dawn Song (UC Berkeley)

Read More

HEIR: A Unified Representation for Cross-Scheme Compilation of Fully...

Song Bian (Beihang University), Zian Zhao (Beihang University), Zhou Zhang (Beihang University), Ran Mao (Beihang University), Kohei Suenaga (Kyoto University), Yier Jin (University of Science and Technology of China), Zhenyu Guan (Beihang University), Jianwei Liu (Beihang University)

Read More