A Survey on Poisoning Attacks Against Supervised Machine Learning
With the rise of artificial intelligence and machine learning in modern computing, one of the major concerns regarding such techniques is to provide privacy and security against adversaries. We present this survey paper to cover the most representative papers in poisoning attacks against supervised machine learning models. We first provide a taxonomy to categorize existing studies and then present detailed summaries for selected papers. We summarize and compare the methodology and limitations of existing literature. We conclude this paper with potential improvements and future directions to further exploit and prevent poisoning attacks on supervised models. We propose several unanswered research questions to encourage and inspire researchers for future work.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningSurveySimilar Papers 제목 키워드 기반
Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures
Recommender systems have become an integral part of online services to help users locate specific information in a sea of data. However, existing studies show that some recommender systems are vulnerable to poisoning att…
Recommendation SystemsSurveyWild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficie…
BIG-bench Machine LearningData PoisoningDeep Partition Aggregation: Provable Defense against General Poisoning Attacks
Adversarial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. A provable defense provides a certificate for each test sample, which is a lower bound on the magnitude of a…
On the Effectiveness of Poisoning against Unsupervised Domain Adaptation
Data poisoning attacks manipulate victim's training data to compromise their model performance, after training. Previous works on poisoning have shown the inability of a small amount of poisoned data at significantly red…
Data PoisoningDomain AdaptationUnsupervised Domain AdaptationDeep Partition Aggregation: Provable Defenses against General Poisoning Attacks
Adversarial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. A provable defense provides a certificate for each test sample, which is a lower bound on the magnitude of a…