BililiCode / ARGD
This is an implementation demo of the IJCAI 2022 paper [Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation](https://arxiv.org/abs/2204.09975) in PyTorch.
☆18Updated this week
Related projects ⓘ
Alternatives and complementary repositories for ARGD
- The code is for our NeurIPS 2019 paper: https://arxiv.org/abs/1910.04749☆31Updated 4 years ago
- Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at IC…☆26Updated 4 years ago
- Implementation of our ICLR 2021 paper: Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples.☆11Updated 3 years ago
- ☆19Updated 3 years ago
- ☆11Updated 4 years ago
- ☆23Updated last year
- ☆45Updated 3 years ago
- Defending against Model Stealing via Verifying Embedded External Features☆32Updated 2 years ago
- Example of the attack described in the paper "Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization"☆21Updated 5 years ago
- ☆25Updated 5 years ago
- RAB: Provable Robustness Against Backdoor Attacks☆39Updated last year
- [ICLR'21] Dataset Inference for Ownership Resolution in Machine Learning☆31Updated 2 years ago
- ☆62Updated 4 years ago
- ☆27Updated 2 years ago
- Craft poisoned data using MetaPoison☆47Updated 3 years ago
- Official implementation of "RelaxLoss: Defending Membership Inference Attacks without Losing Utility" (ICLR 2022)☆45Updated 2 years ago
- ☆11Updated 2 years ago
- ☆18Updated 6 months ago
- How Robust are Randomized Smoothing based Defenses to Data Poisoning? (CVPR 2021)☆12Updated 3 years ago
- ☆32Updated 2 months ago
- Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''☆50Updated last year
- ☆25Updated 5 years ago
- ☆13Updated 2 years ago
- ☆19Updated last year
- ☆25Updated last year
- Code for CVPR2020 paper QEBA: Query-Efficient Boundary-Based Blackbox Attack☆30Updated 3 years ago
- [CVPR 2022] "Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free" by Tianlong Chen*, Zhenyu Zhang*, Yihua Zhang*, Shiyu C…☆25Updated 2 years ago
- ☆41Updated last year
- [NeurIPS 2022] "Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets" by Ruisi Cai*, Zhenyu Zh…☆18Updated 2 years ago
- [NeurIPS'22] Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork. Haotao Wang, Junyuan Hong,…☆13Updated 11 months ago