qilong-zhang / Staircase-sign-methodLinks
Our simple but effective staircase sign method which boosts the transferability of both non-targeted and targeted attacks.
☆18Updated 3 years ago
Alternatives and similar repositories for Staircase-sign-method
Users that are interested in Staircase-sign-method are comparing it to the libraries listed below
Sorting:
- The extension of "Patch-wise Attack for Fooling Deep Neural Network (ECCV2020)", and we aim to boost the success rates of targeted attack…☆28Updated 3 years ago
- ☆27Updated 3 years ago
- Generalized Data-free Universal Adversarial Perturbations in PyTorch☆20Updated 5 years ago
- code for "Feature Importance-aware Transferable Adversarial Attacks"☆87Updated 3 years ago
- ☆71Updated 4 years ago
- Codes for ICLR 2020 paper "Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets"☆70Updated 5 years ago
- Our Team (green hand) 6th Solution for CVPR-2021 AIC-VI: Unrestricted Adversarial Attacks on ImageNet☆26Updated 3 years ago
- Simple yet effective targeted transferable attack (NeurIPS 2021)☆51Updated 3 years ago
- Code for our NeurIPS 2020 paper Practical No-box Adversarial Attacks against DNNs.☆34Updated 5 years ago
- Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.☆61Updated 3 years ago
- Enhancing the Transferability of Adversarial Attacks through Variance Tuning☆90Updated last year
- The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabili…☆20Updated last year
- A Unified Approach to Interpreting and Boosting Adversarial Transferability (ICLR2021)☆31Updated 3 years ago
- Code for our NeurIPS 2020 paper Backpropagating Linearly Improves Transferability of Adversarial Examples.☆42Updated 2 years ago
- Patch-wise iterative attack (accepted by ECCV 2020) to improve the transferability of adversarial examples.☆94Updated 3 years ago
- ☆22Updated 3 years ago
- A PyTorch implementation of universal adversarial perturbation (UAP) which is more easy to understand and implement.☆54Updated 3 years ago
- ☆58Updated 3 years ago
- Codes for CVPR2020 paper "Towards Transferable Targeted Attack".☆15Updated 3 years ago
- Sparse and Imperceivable Adversarial Attacks (accepted to ICCV 2019).☆43Updated 5 years ago
- This repository is the official implementation of [Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks (NeurIPS'22)](http…☆26Updated 2 years ago
- Official repository for "Cross-Domain Transferability of Adversarial Perturbations" (NeurIPS 2019)☆64Updated 4 years ago
- Source of the ECCV22 paper "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity"☆18Updated 10 months ago
- Strongest attack against Feature Scatter and Adversarial Interpolation☆25Updated 6 years ago
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆118Updated 3 years ago
- ☆42Updated 2 years ago
- ☆11Updated 3 years ago
- Code for Boosting fast adversarial training with learnable adversarial initialization (TIP2022)☆29Updated 2 years ago
- Triangle Attack: A Query-efficient Decision-based Adversarial Attack (ECCV 2022)☆17Updated 3 years ago
- [CVPR 2022] Official implementation of the Object-based Diverse Input (ODI) method☆23Updated 3 years ago