Abstract
[Google Meet]
https://meet.google.com/jvq-xkqd-tep
Recent advances in generative AI have enabled remarkable progress in image, video, and multimodal content generation. However, these models can also exhibit undesirable behaviors, including memorization of training data, privacy leakage, and the amplification of societal biases. This talk will examine these challenges in diffusion-based generative models, highlighting their implications for trustworthiness and responsible deployment. We will then discuss emerging approaches for machine unlearning and concept erasure, which aim to selectively remove unwanted knowledge while preserving model utility.
https://meet.google.com/jvq-xkqd-tep
Recent advances in generative AI have enabled remarkable progress in image, video, and multimodal content generation. However, these models can also exhibit undesirable behaviors, including memorization of training data, privacy leakage, and the amplification of societal biases. This talk will examine these challenges in diffusion-based generative models, highlighting their implications for trustworthiness and responsible deployment. We will then discuss emerging approaches for machine unlearning and concept erasure, which aim to selectively remove unwanted knowledge while preserving model utility.
Bio
Vishal M. Patel is a Professor in the Department of Electrical and Computer Engineering (ECE) at Johns Hopkins University. His research focuses on computer vision, machine learning, image processing, medical image analysis, and biometrics. He has received a number of awards including the 2021 IEEE Signal Processing Society (SPS) Pierre-Simon Laplace Early Career Technical Achievement Award, the 2021 NSF CAREER Award, the 2021 IAPR Young Biometrics Investigator Award (YBIA), the 2016 ONR Young Investigator Award, and the 2016 Jimmy Lin Award for Invention. Patel serves as an associate editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence journal and IEEE Transactions on Biometrics, Behavior, and Identity Science. He also chairs the conference subcommittee of IAPR Technical Committee on Biometrics (TC4). He is a fellow of IAPR and IEEE.