| Title | Poisoning Attack against Online Regression Learning with Maximum Loss for Edge Intelligence |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Zhu, Yanxu, Wen, Hong, Zhang, Peng, Han, Wen, Sun, Fan, Jia, Jia |
| Conference Name | 2022 International Conference on Computing, Communication, Perception and Quantum Technology (CCPQT) |
| Keywords | AI Poisoning, artificial intelligence, Computational modeling, Data models, edge computing, edge intelligence, Human Behavior, Market research, online learning, poisoning attack, pubcrawl, quantum computing, regression task, resilience, Resiliency, Scalability, Task Analysis |
| Abstract | Recent trends in the convergence of edge computing and artificial intelligence (AI) have led to a new paradigm of "edge intelligence", which are more vulnerable to attack such as data and model poisoning and evasion of attacks. This paper proposes a white-box poisoning attack against online regression model for edge intelligence environment, which aim to prepare the protection methods in the future. Firstly, the new method selects data points from original stream with maximum loss by two selection strategies; Secondly, it pollutes these points with gradient ascent strategy. At last, it injects polluted points into original stream being sent to target model to complete the attack process. We extensively evaluate our proposed attack on open dataset, the results of which demonstrate the effectiveness of the novel attack method and the real implications of poisoning attack in a case study electric energy prediction application. |
| DOI | 10.1109/CCPQT56151.2022.00037 |
| Citation Key | zhu_poisoning_2022 |
Poisoning Attack against Online Regression Learning with Maximum Loss for Edge Intelligence