TomSheng21 / AdaptGuard
ICCV 2023 - AdaptGuard: Defending Against Universal Attacks for Model Adaptation
☆11Updated 8 months ago
Related projects: ⓘ
- ☆10Updated this week
- Official code for ICML 2024 paper, "Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models"☆13Updated 3 months ago
- [CVPR23] "Understanding and Improving Visual Prompting: A Label-Mapping Perspective" by Aochuan Chen, Yuguang Yao, Pin-Yu Chen, Yihua Zha…☆50Updated last year
- ☆35Updated last year
- NN 2023☆22Updated last year
- A collection of model transferability estimation methods.☆19Updated 7 months ago
- ☆48Updated 5 months ago
- ☆9Updated last year
- The official repository of ECCV 2024 paper "Outlier-Aware Test-time Adaptation with Stable Memory Replay"☆13Updated 2 weeks ago
- ☆22Updated 5 months ago
- ☆56Updated last year
- Official code for ICCV 2023 paper, "Improving Zero-Shot Generalization for CLIP with Synthesized Prompts"☆88Updated 6 months ago
- [NeurIPS 2021] "Class-Disentanglement and Applications in Adversarial Detection and Defense"☆43Updated 2 years ago
- Code for Transferable Unlearnable Examples☆17Updated last year
- ☆24Updated 3 months ago
- ☆16Updated last year
- Improving Adversarial Robustness via Mutual Information Estimation☆8Updated 5 months ago
- ☆15Updated 4 months ago
- [ICLR 2024 Spotlight] "Negative Label Guided OOD Detection with Pretrained Vision-Language Models"☆19Updated 6 months ago
- ECCV2024: Adversarial Prompt Tuning for Vision-Language Models☆19Updated last month
- ☆79Updated 2 years ago
- This is the source code for Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score (ICML2023).☆33Updated 4 months ago
- Official code for ICLR 2024 paper, "A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation"☆61Updated 4 months ago
- code released for our TIP 2021 paper "Adversarial Domain Adaptation with Prototype-based Normalized Output Conditioner"☆15Updated last year
- Towards Defending against Adversarial Examples via Attack-Invariant Features☆9Updated 11 months ago
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆31Updated 4 months ago
- Code of Data-Free Knowledge Distillation via Feature Exchange and Activation Region Constraint☆15Updated 10 months ago
- About Code Release for "CLIPood: Generalizing CLIP to Out-of-Distributions" (ICML 2023), https://arxiv.org/abs/2302.00864☆58Updated last year
- CVPR2023: Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples☆20Updated last year
- [NeurIPS 2021] “When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?”☆45Updated 2 years ago