qilong-zhang / Staircase-sign-method
Our simple but effective staircase sign method which boosts the transferability of both non-targeted and targeted attacks.
☆17Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for Staircase-sign-method
- The extension of "Patch-wise Attack for Fooling Deep Neural Network (ECCV2020)", and we aim to boost the success rates of targeted attack…☆26Updated 2 years ago
- Our Team (green hand) 6th Solution for CVPR-2021 AIC-VI: Unrestricted Adversarial Attacks on ImageNet☆25Updated 2 years ago
- ☆26Updated 2 years ago
- Codes for CVPR2020 paper "Towards Transferable Targeted Attack".☆15Updated 2 years ago
- Simple yet effective targeted transferable attack (NeurIPS 2021)☆47Updated 2 years ago
- Codes for ICLR 2020 paper "Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets"☆70Updated 4 years ago
- Patch-wise iterative attack (accepted by ECCV 2020) to improve the transferability of adversarial examples.☆89Updated 2 years ago
- The code of our AAAI 2021 paper "Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-transform Domain"☆14Updated 3 years ago
- Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability☆24Updated 2 years ago
- [NeurIPS 2023] Boosting Adversarial Transferability by Achieving Flat Local Maxima☆27Updated 8 months ago
- A Unified Approach to Interpreting and Boosting Adversarial Transferability (ICLR2021)☆28Updated 2 years ago
- code for "Feature Importance-aware Transferable Adversarial Attacks"☆77Updated 2 years ago
- ☆55Updated 2 years ago
- Code for our NeurIPS 2020 paper Practical No-box Adversarial Attacks against DNNs.☆33Updated 3 years ago
- ☆21Updated last year
- Official code for "Boosting the Adversarial Transferability of Surrogate Model with Dark Knowledge"☆11Updated 11 months ago
- Source of the ECCV22 paper "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity"☆17Updated last year
- Enhancing the Transferability of Adversarial Attacks through Variance Tuning☆81Updated 8 months ago
- Generalized Data-free Universal Adversarial Perturbations in PyTorch☆17Updated 4 years ago
- Spectrum simulation attack (ECCV'2022 Oral) towards boosting the transferability of adversarial examples☆90Updated 2 years ago
- A PyTorch implementation of universal adversarial perturbation (UAP) which is more easy to understand and implement.☆54Updated 2 years ago
- ☆68Updated 3 years ago
- [CVPR 2022] Official implementation of the Object-based Diverse Input (ODI) method☆21Updated 2 years ago
- Code for the paper "StyLess: Boosting the Transferability of Adversarial Examples" (CVPR 2023)☆24Updated last year
- Decision-based Adversarial Attack with Frequency Mixup☆21Updated last year
- Code for Adv-watermark: A novel watermark perturbation for adversarial examples (ACM MM2020)☆40Updated 4 years ago
- Official PyTorch implementation of "Towards Efficient Data Free Black-Box Adversarial Attack" (CVPR 2022)☆15Updated 2 years ago
- This repository is the official implementation of [Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks (NeurIPS'22)](http…☆25Updated last year
- The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabili…☆15Updated 3 months ago
- Boosting Transferability through Enhanced Momentum☆14Updated 8 months ago