illidanlab / inversion-influence-function
Official codes for "Understanding Deep Gradient Leakage via Inversion Influence Functions", NeurIPS 2023
☆15Updated last year
Alternatives and similar repositories for inversion-influence-function:
Users that are interested in inversion-influence-function are comparing it to the libraries listed below
- [USENIX Security 2022] Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture☆16Updated 2 years ago
- ☆10Updated 2 years ago
- ☆24Updated 2 years ago
- [ICLR2024] "Backdoor Federated Learning by Poisoning Backdoor-Critical Layers"☆28Updated last month
- This is the repository that introduces research topics related to protecting intellectual property (IP) of AI from a data-centric perspec…☆22Updated last year
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆48Updated 2 years ago
- A pytorch implementation of the paper "Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage".☆58Updated 2 years ago
- ☆15Updated 2 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆25Updated 2 months ago
- ☆67Updated 2 years ago
- A Fine-grained Differentially Private Federated Learning against Leakage from Gradients☆12Updated 2 years ago
- code release for "Unrolling SGD: Understanding Factors Influencing Machine Unlearning" published at EuroS&P'22☆22Updated 2 years ago
- The official implement of paper "Does Federated Learning Really Need Backpropagation?"☆23Updated last year
- Implementation of the paper : "Membership Inference Attacks Against Machine Learning Models", Shokri et al.☆57Updated 5 years ago
- [NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gao…☆67Updated 10 months ago
- [CCS 2021] "DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation" by Boxin Wang*, Fan Wu*, Yunhui Long…☆37Updated 3 years ago
- ICML 2022 code for "Neurotoxin: Durable Backdoors in Federated Learning" https://arxiv.org/abs/2206.10341☆67Updated last year
- Code for the paper: Label-Only Membership Inference Attacks☆64Updated 3 years ago
- Official implementation of "Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective"☆55Updated last year
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆56Updated last year
- Code for Backdoor Attacks Against Dataset Distillation☆32Updated last year
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆29Updated 2 years ago
- ☆12Updated 8 months ago
- R-GAP: Recursive Gradient Attack on Privacy [Accepted at ICLR 2021]☆34Updated last year
- [ICML 2023] Are Diffusion Models Vulnerable to Membership Inference Attacks?☆32Updated 4 months ago
- ☆23Updated 3 years ago
- 🔒 Implementation of Shokri et al(2016) "Membership Inference Attacks against Machine Learning Models"☆34Updated 2 years ago
- ☆29Updated 2 years ago
- Camouflage poisoning via machine unlearning☆16Updated 2 years ago
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆11Updated 3 months ago