PKU-ML / AdvNotRealFeaturesLinks
Official Code for reproductivity of the NeurIPS 2023 paper: Adversarial Examples Are Not Real Features
☆17Updated last year
Alternatives and similar repositories for AdvNotRealFeatures
Users that are interested in AdvNotRealFeatures are comparing it to the libraries listed below
Sorting:
- Code repository for CVPR2024 paper 《Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness》☆22Updated last year
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning☆18Updated last year
- Towards Defending against Adversarial Examples via Attack-Invariant Features☆12Updated 2 years ago
- Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).☆33Updated 2 years ago
- [CVPR 2023] Adversarial Robustness via Random Projection Filters☆14Updated 2 years ago
- SEAT☆21Updated 2 years ago
- ☆10Updated 3 years ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆40Updated last year
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 11 months ago
- Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)☆33Updated 2 years ago
- ☆20Updated 7 months ago
- ☆102Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆21Updated last year
- [CVPR23] "Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations" by Lei Hsi…☆24Updated last month
- ☆53Updated last year
- [ICLR 2023] Official repository of the paper "Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning"☆18Updated 2 years ago
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆48Updated last year
- ☆38Updated last year
- AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models (ICCV 2023)☆19Updated 2 years ago
- [CVPR 2022 oral] Subspace Adversarial Training☆27Updated 2 years ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 11 months ago
- ☆43Updated 2 years ago
- ☆78Updated last year
- ☆21Updated 3 years ago
- Code Repo for the NeurIPS 2023 paper "VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models"☆27Updated last month
- ☆53Updated 2 years ago
- ☆14Updated 3 years ago
- ☆23Updated 2 years ago
- ☆15Updated 8 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆58Updated last year