ebagdasa / adversarial_illusionsLinks
Code for "Adversarial Illusions in Multi-Modal Embeddings"
☆27Updated last year
Alternatives and similar repositories for adversarial_illusions
Users that are interested in adversarial_illusions are comparing it to the libraries listed below
Sorting:
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆55Updated 9 months ago
- This is an official repository for Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study (ICCV2023…☆24Updated 2 years ago
- ☆13Updated last year
- ☆102Updated last year
- Official repo to reproduce the paper "How to Backdoor Diffusion Models?" published at CVPR 2023☆92Updated last month
- [ICML 2023] Are Diffusion Models Vulnerable to Membership Inference Attacks?☆41Updated last year
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment☆28Updated last week
- 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
- [CVPR 2023] The official implementation of our CVPR 2023 paper "Detecting Backdoors During the Inference Stage Based on Corruption Robust…☆23Updated 2 years ago
- ☆53Updated last year
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆63Updated 10 months ago
- Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)☆39Updated last year
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆19Updated 2 years ago
- Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)☆34Updated 3 months ago
- ☆25Updated 2 years ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdf☆21Updated last year
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning☆18Updated last year
- ☆21Updated last year
- ☆44Updated 3 years ago
- ☆31Updated 3 years ago
- ☆27Updated 2 years ago
- This is the source code for MEA-Defender. Our paper is accepted by the IEEE Symposium on Security and Privacy (S&P) 2024.☆29Updated last year
- This is the official implementation of our paper 'Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protecti…☆57Updated last year
- [S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models☆18Updated 8 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆40Updated last year
- Code for identifying natural backdoors in existing image datasets.☆15Updated 3 years ago
- ☆84Updated 4 years ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆23Updated 11 months ago
- ☆13Updated 3 years ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆58Updated last year