Biblio

Filters: Author is Yang, Qiang  [Clear All Filters]
2022-06-08
Ong, Ding Sheng, Seng Chan, Chee, Ng, Kam Woh, Fan, Lixin, Yang, Qiang.  2021.  Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attacks. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). :3629–3638.
Ever since Machine Learning as a Service emerges as a viable business that utilizes deep learning models to generate lucrative revenue, Intellectual Property Right (IPR) has become a major concern because these deep learning models can easily be replicated, shared, and re-distributed by any unauthorized third parties. To the best of our knowledge, one of the prominent deep learning models - Generative Adversarial Networks (GANs) which has been widely used to create photorealistic image are totally unprotected despite the existence of pioneering IPR protection methodology for Convolutional Neural Networks (CNNs). This paper therefore presents a complete protection framework in both black-box and white-box settings to enforce IPR protection on GANs. Empirically, we show that the proposed method does not compromise the original GANs performance (i.e. image generation, image super-resolution, style transfer), and at the same time, it is able to withstand both removal and ambiguity attacks against embedded watermarks. Codes are available at https://github.com/dingsheng-ong/ipr-gan.
2022-09-20
Yao, Pengchao, Hao, Weijie, Yan, Bingjing, Yang, Tao, Wang, Jinming, Yang, Qiang.  2021.  Game-Theoretic Model for Optimal Cyber-Attack Defensive Decision-Making in Cyber-Physical Power Systems. 2021 IEEE 5th Conference on Energy Internet and Energy System Integration (EI2). :2359—2364.

Cyber-Physical Power Systems (CPPSs) currently face an increasing number of security attacks and lack methods for optimal proactive security decisions to defend the attacks. This paper proposed an optimal defensive method based on game theory to minimize the system performance deterioration of CPPSs under cyberspace attacks. The reinforcement learning algorithmic solution is used to obtain the Nash equilibrium and a set of metrics of system vulnerabilities are adopted to quantify the cost of defense against cyber-attacks. The minimax-Q algorithm is utilized to obtain the optimal defense strategy without the availability of the attacker's information. The proposed solution is assessed through experiments based on a realistic power generation microsystem testbed and the numerical results confirmed its effectiveness.

2017-03-20
Wang, Yinan, Zeng, Sicheng, Yang, Qiang, Lin, Zhiyun, Xu, Wenyuan, Yan, Gangfeng.  2016.  A new framework of electrical cyber physical systems. :1334–1339.

This paper establishes a new framework for electrical cyber-physical systems (ECPSs). The communication network is designed by the characteristics of a power grid. The interdependent relationship of communication networks and power grids is described by data-uploading channels and commands-downloading channels. Control strategies (such as load shedding and relay protection) are extended to this new framework for analyzing the performance of ECPSs under several attack scenarios. The fragility of ECPSs under cyber attacks (DoS attack and false data injection attack) and the effectiveness of relay protection policies are verified by experimental results.

2017-05-19
Pan, Weike, Yang, Qiang, Duan, Yuchao, Ming, Zhong.  2016.  Transfer Learning for Semisupervised Collaborative Recommendation. ACM Trans. Interact. Intell. Syst.. 6:10:1–10:21.

Users’ online behaviors such as ratings and examination of items are recognized as one of the most valuable sources of information for learning users’ preferences in order to make personalized recommendations. But most previous works focus on modeling only one type of users’ behaviors such as numerical ratings or browsing records, which are referred to as explicit feedback and implicit feedback, respectively. In this article, we study a Semisupervised Collaborative Recommendation (SSCR) problem with labeled feedback (for explicit feedback) and unlabeled feedback (for implicit feedback), in analogy to the well-known Semisupervised Learning (SSL) setting with labeled instances and unlabeled instances. SSCR is associated with two fundamental challenges, that is, heterogeneity of two types of users’ feedback and uncertainty of the unlabeled feedback. As a response, we design a novel Self-Transfer Learning (sTL) algorithm to iteratively identify and integrate likely positive unlabeled feedback, which is inspired by the general forward/backward process in machine learning. The merit of sTL is its ability to learn users’ preferences from heterogeneous behaviors in a joint and selective manner. We conduct extensive empirical studies of sTL and several very competitive baselines on three large datasets. The experimental results show that our sTL is significantly better than the state-of-the-art methods.