Poster "membership inference attacks" Papers

13 papers found

Adversarial Machine Unlearning

Zonglin Di, Sixie Yu, Yevgeniy Vorobeychik et al.

ICLR 2025arXiv:2406.07687
11
citations

CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion

Joshua Kazdan, Hao Sun, Jiaqi Han et al.

ICLR 2025arXiv:2409.07025
2
citations

Exploring the limits of strong membership inference attacks on large language models

Jamie Hayes, I Shumailov, Christopher A. Choquette-Choo et al.

NEURIPS 2025arXiv:2505.18773
12
citations

How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning

Yao Tong, Jiayuan Ye, Sajjad Zarifzadeh et al.

ICLR 2025

LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models

Yihao LIU, Xinqi Lyu, Dong Wang et al.

NEURIPS 2025

Membership Inference Attacks with False Discovery Rate Control

Chenxu Zhao, Wei Qian, Aobo Chen et al.

ICCV 2025arXiv:2508.07066
1
citations

Practical Bayes-Optimal Membership Inference Attacks

Marcus Lassila, Johan Oestman, Khac-Hoang Ngo et al.

NEURIPS 2025arXiv:2505.24089
2
citations

What Really is a Member? Discrediting Membership Inference via Poisoning

Neal Mangaokar, Ashish Hooda, Zhuohang Li et al.

NEURIPS 2025arXiv:2506.06003
1
citations

Fast Adversarial Attacks on Language Models In One GPU Minute

Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan et al.

ICML 2024arXiv:2402.15570
72
citations

Low-Cost High-Power Membership Inference Attacks

Sajjad Zarifzadeh, Philippe Liu, Reza Shokri

ICML 2024arXiv:2312.03262
80
citations

Membership Inference Attacks on Diffusion Models via Quantile Regression

Shuai Tang, Steven Wu, Sergul Aydore et al.

ICML 2024arXiv:2312.05140
21
citations

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Zhenlong Liu, Lei Feng, HUIPING ZHUANG et al.

ICML 2024arXiv:2402.05453
5
citations

Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGD

Jonggyu Jang, Seongjin Hwang, Hyun Jong Yang

ICML 2024