https://www.daedluz.com/posts/Recent content in Posts on Min Chun ChenHugo -- 0.148.2en-usmchen12@umbc.edu (Michael (Min Chun Chen))mchen12@umbc.edu (Michael (Min Chun Chen))Tue, 12 Aug 2025 01:16:16 -0400https://www.daedluz.com/posts/membership-inference-attack-with-cumulative-topological-distance/Tue, 12 Aug 2025 01:16:16 -0400mchen12@umbc.edu (Michael (Min Chun Chen))https://www.daedluz.com/posts/membership-inference-attack-with-cumulative-topological-distance/<h1 id="introduction">Introduction</h1> <p>As machine learning models become increasingly powerful and pervasive, concerns about privacy in their deployment have grown. One notable risk comes from <strong>membership inference attacks</strong>, where an adversary attempts to determine whether a particular data point was used to train a given model. For example, in healthcare, a membership inference attack could reveal if someone participated in a clinical study, threatening patient confidentiality. This risk motivates my work in this post, where I document my recent experiment investigating the possibility in using cumulative topological distance in membership inference attacks.</p>