VincentNi0107 / BadVLMDriver
☆9Updated 9 months ago
Alternatives and similar repositories for BadVLMDriver:
Users that are interested in BadVLMDriver are comparing it to the libraries listed below
- MSF-ADV is a novel physical-world adversarial attack method, which can fool the Multi Sensor Fusion (MSF) based autonomous driving (AD) p…☆78Updated 3 years ago
- [TMLR'24] On the Adversarial Robustness of Camera-based 3D Object Detection☆24Updated 10 months ago
- One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models☆45Updated 2 months ago
- The Pytorch implementation for the paper "Fusion is Not Enough: Single Modal Attack on Fusion Models for 3D Object Detection"☆11Updated 11 months ago
- [CVPR 2022] Shape-invariant Adversarial Point Clouds☆43Updated last year
- ☆37Updated 2 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]☆54Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆34Updated 10 months ago
- ☆35Updated 2 years ago
- ☆63Updated 3 months ago
- ☆11Updated last year
- Implementation of "Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches"☆21Updated 2 years ago
- [CVPR 2023] Understanding the Robustness of 3D Object Detection With Bird's-Eye-View Representations in Autonomous Driving☆27Updated 11 months ago
- ☆16Updated 3 years ago
- ☆43Updated last year
- [NeurIPS'22] GAMA: Generative Adversarial Multi-Object Scene Attacks☆15Updated last year
- AutoTrust, a groundbreaking benchmark designed to assess the trustworthiness of DriveVLMs. This work aims to enhance public safety by ens…☆38Updated 2 months ago
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Gener…☆14Updated 4 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajector…☆21Updated 3 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆40Updated 8 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆28Updated last year
- ☆23Updated 2 years ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆50Updated 10 months ago
- A Backdoor Attack against 3D Point Cloud Classifiers (ICCV2021)☆18Updated 3 years ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2…☆47Updated 4 months ago
- [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset☆46Updated 10 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆23Updated 4 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆24Updated 4 months ago
- The code of "Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds" CVPR 2024☆27Updated 11 months ago
- [CVPR2024 Highlight] The official repo for paper "Abductive Ego-View Accident Video Understanding for Safe Driving Perception"☆42Updated 2 months ago