reds-lab / CLIP-MIALinks
This is an official repository for Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study (ICCV2023).
☆23Updated last year
Alternatives and similar repositories for CLIP-MIA
Users that are interested in CLIP-MIA are comparing it to the libraries listed below
Sorting:
- [ICML 2023] Are Diffusion Models Vulnerable to Membership Inference Attacks?☆39Updated 11 months ago
- ☆25Updated 2 years ago
- [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robust…☆23Updated 2 years ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Updated last year
- ☆20Updated last year
- [NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes☆12Updated 2 years ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆52Updated 7 months ago
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆60Updated 8 months ago
- ☆13Updated last year
- [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"☆29Updated last week
- ☆31Updated 3 years ago
- Source code and scripts for the paper "Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks"☆18Updated 8 months ago
- Official repo for An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization☆15Updated last year
- ☆11Updated 2 years ago
- ☆24Updated 11 months ago
- ☆50Updated last year
- ☆24Updated last year
- ☆60Updated 2 years ago
- Backdoor Safety Tuning (NeurIPS 2023 & 2024 Spotlight)☆26Updated 9 months ago
- ☆24Updated 2 years ago
- Github repo for One-shot Neural Backdoor Erasing via Adversarial Weight Masking (NeurIPS 2022)☆15Updated 2 years ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆21Updated last year
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆92Updated 3 months ago
- ☆20Updated last year
- ☆20Updated 5 months ago
- ☆27Updated 2 years ago
- ☆18Updated 2 years ago
- The official implementation of USENIX Security'23 paper "Meta-Sift" -- Ten minutes or less to find a 1000-size or larger clean subset on …☆19Updated 2 years ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated last year
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated 10 months ago