13 results found Sort:

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
Created 2020-04-08
510 commits to master branch, last one about a month ago
[NeurIPS'24] "Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration"
Created 2023-09-15
1 commits to main branch, last one 5 months ago
8
128
unknown
9
[AAAI'25 Oral] "MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector".
Created 2023-12-20
1 commits to main branch, last one 7 days ago
21
122
mit
4
Privacy Preserving Collaborative Encrypted Network Traffic Classification (Differential Privacy, Federated Learning, Membership Inference Attack, Encrypted Traffic Classification)
Created 2019-12-01
61 commits to master branch, last one about a year ago
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Denn...
Created 2023-10-12
49 commits to master branch, last one about a month ago
[NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu
Created 2023-02-03
105 commits to public branch, last one 9 months ago
5
63
unknown
3
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024
Created 2024-05-28
13 commits to main branch, last one 2 months ago
Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch.
Created 2021-05-31
130 commits to main branch, last one 2 months ago
Official implementation of "When Machine Unlearning Jeopardizes Privacy" (ACM CCS 2021)
Created 2021-09-13
4 commits to main branch, last one 2 years ago
🔒 Implementation of Shokri et al(2016) "Membership Inference Attacks against Machine Learning Models"
Created 2022-07-11
38 commits to main branch, last one 2 years ago
Min-K%++: Improved baseline for detecting pre-training data of LLMs https://arxiv.org/abs/2404.02936
Created 2024-04-02
12 commits to main branch, last one 6 months ago