Label-Only Membership Inference Attack Based on Model Explanation
Sign Up to like & getrecommendations! Published in 2024 at "Neural Processing Letters"
DOI: 10.1007/s11063-024-11682-1
Abstract: It is well known that machine learning models (e.g., image recognition) can unintentionally leak information about the training set. Conventional membership inference relies on posterior vectors, and this task becomes extremely difficult when the posterior… read more here.
Keywords: membership inference; inference; label membership; inference attack ... See more keywords