| Title | A Survey on Data Poisoning Attacks and Defenses |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Fan, Jiaxin, Yan, Qi, Li, Mohan, Qu, Guanqun, Xiao, Yang |
| Conference Name | 2022 7th IEEE International Conference on Data Science in Cyberspace (DSC) |
| Keywords | AI Poisoning, Availability Attack, Data collection, Data models, data poisoning, Data Science, Human Behavior, machine learning, pubcrawl, resilience, Resiliency, Scalability, security, targeted attack, Training, Training data |
| Abstract | With the widespread deployment of data-driven services, the demand for data volumes continues to grow. At present, many applications lack reliable human supervision in the process of data collection, which makes the collected data contain low-quality data or even malicious data. This low-quality or malicious data make AI systems potentially face much security challenges. One of the main security threats in the training phase of machine learning is data poisoning attacks, which compromise model integrity by contaminating training data to make the resulting model skewed or unusable. This paper reviews the relevant researches on data poisoning attacks in various task environments: first, the classification of attacks is summarized, then the defense methods of data poisoning attacks are sorted out, and finally, the possible research directions in the prospect. |
| DOI | 10.1109/DSC55868.2022.00014 |
| Citation Key | fan_survey_2022 |
A Survey on Data Poisoning Attacks and Defenses