MiracleHH / nas_privacy
Official Code Implementation for the CCS 2022 Paper "On the Privacy Risks of Cell-Based NAS Architectures"
☆10Updated last year
Related projects: ⓘ
- ☆23Updated last year
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated 11 months ago
- [NeurIPS 2021] "Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks" by Yon…☆13Updated 2 years ago
- ☆18Updated 3 years ago
- Official Implementation of NIPS 2022 paper Pre-activation Distributions Expose Backdoor Neurons☆13Updated last year
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆30Updated last year
- Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…☆26Updated 4 years ago
- [Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping☆10Updated 4 years ago
- ☆12Updated 2 years ago
- [CVPR 2022] "Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free" by Tianlong Chen*, Zhenyu Zhang*, Yihua Zhang*, Shiyu C…☆24Updated last year
- Defending Against Backdoor Attacks Using Robust Covariance Estimation☆20Updated 3 years ago
- ☆19Updated 2 years ago
- ☆18Updated 4 months ago
- [Preprint] Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis☆11Updated 2 years ago
- ☆9Updated 3 years ago
- Pytorch implementation of backdoor unlearning.☆15Updated 2 years ago
- ☆19Updated 2 years ago
- Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"☆52Updated last year
- [ICLR 2022] Boosting Randomized Smoothing with Variance Reduced Classifiers☆11Updated 2 years ago
- Camouflage poisoning via machine unlearning☆14Updated last year
- ☆20Updated last year
- ☆12Updated 2 years ago
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆14Updated last year
- [NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zh…☆18Updated last year
- The implementatin of our ICLR 2021 work: Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits☆18Updated 3 years ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆25Updated 8 months ago
- The code is for our NeurIPS 2019 paper: https://arxiv.org/abs/1910.04749☆31Updated 4 years ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆16Updated last year
- Defending against Model Stealing via Verifying Embedded External Features☆31Updated 2 years ago
- [ICLR 2021: Spotlight] Source code for the paper "A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Infer…☆15Updated 2 years ago