IBM / composite-advLinks
[CVPR23] "Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations" by Lei Hsiung, Yun-Yun Tsai, Pin-Yu Chen, and Tsung-Yi Ho.
☆24Updated last month
Alternatives and similar repositories for composite-adv
Users that are interested in composite-adv are comparing it to the libraries listed below
Sorting:
- ☆78Updated last year
- Code repository for CVPR2024 paper 《Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness》☆22Updated last year
- A curated list of papers for the transferability of adversarial examples☆73Updated last year
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models☆53Updated 2 months ago
- Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks(CVPR2023)☆17Updated 2 years ago
- Code for Transferable Unlearnable Examples☆21Updated 2 years ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- ☆31Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆21Updated last year
- Code for the paper "Autoregressive Perturbations for Data Poisoning" (NeurIPS 2022)☆20Updated last year
- Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).☆33Updated 2 years ago
- Official implementation of the ICCV2023 paper: Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregatio…☆27Updated 2 years ago
- ☆35Updated 2 years ago
- Revisiting Transferable Adversarial Images (TPAMI 2025)☆130Updated last month
- [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robust…☆23Updated 2 years ago
- TIFS2022: Decision-based Adversarial Attack with Frequency Mixup☆23Updated 2 years ago
- ☆37Updated last year
- Code for Prior-Guided Adversarial Initialization for Fast Adversarial Training (ECCV2022)☆27Updated 2 years ago
- Code for the paper "Better Diffusion Models Further Improve Adversarial Training" (ICML 2023)☆144Updated 2 years ago
- A list of papers in NeurIPS 2022 related to adversarial attack and defense / AI security.☆73Updated 2 years ago
- Source of the ECCV22 paper "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity"☆18Updated 7 months ago
- official PyTorch implement of Towards Adversarial Attack on Vision-Language Pre-training Models☆64Updated 2 years ago
- ICCV 2021, We find most existing triggers of backdoor attacks in deep learning contain severe artifacts in the frequency domain. This Rep…☆45Updated 3 years ago
- [ICLR 2022] "Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?" by Yonggan Fu, Shunyao Zhang, Shang Wu…☆34Updated 3 years ago
- ☆23Updated 2 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆34Updated 2 years ago
- ☆118Updated 3 weeks ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]☆63Updated 2 years ago
- Code for LAS-AT: Adversarial Training with Learnable Attack Strategy (CVPR2022)☆117Updated 3 years ago
- ☆20Updated 7 months ago