Survey: Leakage and Privacy at Inference Time
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients' sensitive data. We provide a comprehensive survey of contemporary advances on several fronts, covering involuntary data leakage which is natural to ML models, potential malevolent leakage which is caused by privacy attacks, and currently available defence mechanisms. We focus on inference-time leakage, as the most likely scenario for publicly available models. We first discuss what leakage is in the context of different data, tasks, and model architectures. We then propose a taxonomy across involuntary and malevolent leakage, available defences, followed by the currently available assessment metrics and applications. We conclude with outstanding challenges and open questions, outlining some promising directions for future research.
Code (0)
등록된 구현이 없습니다.
Tasks
SurveySimilar Papers 제목 키워드 기반
A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency
Federated learning (FL) has emerged as a secure paradigm for collaborative training among clients. Without data centralization, FL allows clients to share local information in a privacy-preserving manner. This approach h…
Federated LearningPrivacy PreservingSurveyMembership Inference Attack Susceptibility of Clinical Language Models
Deep Neural Network (DNN) models have been shown to have high empirical privacy leakages. Clinical language models (CLMs) trained on clinical data have been used to improve performance in biomedical natural language proc…
Inference AttackMembership Inference AttackPrivacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions
The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on e…
Federated LearningPrivacy PreservingSurveyPrivacy Leakage Avoidance with Switching Ensembles
We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, wheth…
BIG-bench Machine LearningPrivacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent
Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's…
Language ModelingLanguage ModellingPrivacy Preserving