ziquanliu / CVPR2023-TWINS
Official code for "TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization", CVPR 2023
☆13Updated last year
Related projects ⓘ
Alternatives and complementary repositories for CVPR2023-TWINS
- [NeurIPS 2021] “When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?”☆46Updated 2 years ago
- This is the official code for "Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better"☆39Updated 3 years ago
- ☆17Updated last year
- Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).☆31Updated last year
- [NeurIPS 2021] "Class-Disentanglement and Applications in Adversarial Detection and Defense"☆43Updated 2 years ago
- ☆12Updated 2 years ago
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆23Updated last year
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆18Updated 2 months ago
- SEAT☆19Updated last year
- Official implementation of "When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture" published at Neur…☆27Updated last month
- Implementation for <Robust Weight Perturbation for Adversarial Training> in IJCAI'22.☆14Updated 2 years ago
- Phase-aware Adversarial Defense for Improving Adversarial Robustness☆11Updated last year
- [NeurIPS 2023] Codes for DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification☆23Updated 8 months ago
- Official implementation of the ICCV2023 paper: Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregatio…☆20Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆17Updated 7 months ago
- [ICLR 2023] Official repository of the paper "Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning"☆17Updated last year
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated last year
- Official repository for "On Improving Adversarial Transferability of Vision Transformers" (ICLR 2022--Spotlight)☆69Updated last year
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆37Updated 5 months ago
- Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off☆29Updated 2 years ago
- Removing Adversarial Noise in Class Activation Feature Space☆13Updated last year
- ☆9Updated last year
- ☆46Updated last year
- A Unified Approach to Interpreting and Boosting Adversarial Transferability (ICLR2021)☆28Updated 2 years ago
- Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks(CVPR2023)☆17Updated last year
- CVPR 2023 generalist☆15Updated last year
- Data-Efficient Backdoor Attacks☆18Updated 2 years ago
- ☆19Updated 2 years ago
- Towards Defending against Adversarial Examples via Attack-Invariant Features☆8Updated last year
- ☆16Updated last year