zzd1992 / Adversarial-Defense-by-Suppressing-High-Frequencies
An efficient adversarial defense method with strong insights which won the fifth place of the IJCAI-2019 Alibaba Adversarial AI Challenge.
☆11Updated 4 years ago
Related projects: ⓘ
- A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks (AAAI'20)☆11Updated 4 years ago
- Universal Adversarial Networks☆33Updated 6 years ago
- The implementation of 'Curls & Whey: Boosting Black-Box Adversarial Attacks' in pytorch☆60Updated 5 years ago
- ☆41Updated last year
- Improving the Generalization of Adversarial Training with Domain Adaptation☆31Updated 5 years ago
- Implementation of the Biased Boundary Attack for the NeurIPS 2018 Adversarial Vision Challenge☆13Updated 4 years ago
- ☆46Updated 3 years ago
- This is PyTorch Implementation of Universal Adversarial Perturbation (https://arxiv.org/abs/1610.08401)☆43Updated 5 years ago
- white box adversarial attack☆37Updated 3 years ago
- Image Super-Resolution as a Defense Against Adversarial Attacks☆87Updated 5 years ago
- AAAI 2019 oral presentation☆49Updated last month
- Implementation of the Boundary Attack algorithm as described in Brendel, Wieland, Jonas Rauber, and Matthias Bethge. "Decision-Based Adve…☆90Updated 3 years ago
- Ensemble Adversarial Training on MNIST with pytorch☆20Updated 5 years ago
- Code for Black-Box Adversarial Attack with Transferable Model-based Embedding☆55Updated 4 years ago
- ☆76Updated 3 years ago
- For Competition on Adversarial Attacks and Defenses 2018☆40Updated 5 years ago
- Code for CVPR2020 paper QEBA: Query-Efficient Boundary-Based Blackbox Attack☆30Updated 3 years ago
- Mitigating Adversarial Effects Through Randomization☆116Updated 6 years ago
- Implementation for "Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks"