Back
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
@inproceedings{wen_privacy_2024, title = {Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models}, booktitle = {Proceedings of the Thirty-Eighth Annual Conference on Neural Information Processing Systems}, organization = {NeurIPS}, year = {2024}, slug = {wen_privacy_2024}, author = {Wen, Yuxin and Marchyok, Leo and Hong, Sanghyun and Geiping, Jonas and and Goldstein, Tom and Carlini, Nicolas}, url = {https://openreview.net/forum?id=KppBAWJbry} }
More information