(Peer-Reviewed) Universal Adversarial Examples and Perturbations for Quantum Classifiers
Weiyuan Gong ¹, Dong-Ling Deng 邓东灵 ¹ ²
¹ Center for Quantum Information, IIIS, Tsinghua University, Beijing 100084, People's Republic of China 清华大学 交叉信息研究院 量子信息中心
² Shanghai Qi Zhi Institute, 41th Floor, AI Tower, No. 701 Yunjin Road, Xuhui District, Shanghai 200232, China 上海期智研究院
National Science Review, 2021-07-22
Abstract
Quantum machine learning explores the interplay between machine learning and quantum physics, which may lead to unprecedented perspectives for both fields. In fact, recent works have shown strong evidences that quantum computers could outperform classical computers in solving certain notable machine learning tasks. Yet, quantum learning systems may also suffer from the vulnerability problem: adding a tiny carefully-crafted perturbation to the legitimate input data would cause the systems to make incorrect predictions at a notably high confidence level.
In this paper, we study the universality of adversarial examples and perturbations for quantum classifiers. Through concrete examples involving classifications of real-life images and quantum phases of matter, we show that there exist universal adversarial examples that can fool a set of different quantum classifiers. We prove that for a set of k classifiers with each receiving input data of n qubits, an O(ln k/2ⁿ) increase of the perturbation strength is enough to ensure a moderate universal adversarial risk.
In addition, for a given quantum classifier we show that there exist universal adversarial perturbations, which can be added to different legitimate samples and make them to be adversarial examples for the classifier.
Our results reveal the universality perspective of adversarial attacks for quantum machine learning systems, which would be crucial for practical applications of both near-term and future quantum technologies in solving machine learning problems.
Genetic algorithm assisted meta-atom design for high-performance metasurface optics
Zhenjie Yu, Moxin Li, Zhenyu Xing, Hao Gao, Zeyang Liu, Shiliang Pu, Hui Mao, Hong Cai, Qiang Ma, Wenqi Ren, Jiang Zhu, Cheng Zhang
Opto-Electronic Science
2024-09-20
Surface-patterned chalcogenide glasses with high-aspect-ratio microstructures for long-wave infrared metalenses
Zhaofeng Gu, Yixiao Gao, Kongsi Zhou, Junyang Ge, Chen Xu, Lei Xu, Mohsen Rahmani, Ran Jiang, Yimin Chen, Zijun Liu, Chenjie Gu, Yaoguang Ma, Jianrong Qiu, Xiang Shen
Opto-Electronic Science
2024-09-03
Racemic dielectric metasurfaces for arbitrary terahertz polarization rotation and wavefront manipulation
Jie Li, Xueguang Lu, Hui Li, Chunyu Song, Qi Tan, Yu He, Jingyu Liu, Li Luo, Tingting Tang, Tingting Liu, Hang Xu, Shuyuan Xiao, Wanxia Huang, Yun Shen, Yan Zhang, Yating Zhang, Jianquan Yao
Opto-Electronic Advances
2024-08-28