Vinsonzyh / BlueSuffix
[ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
β16Updated last week
Alternatives and similar repositories for BlueSuffix:
Users that are interested in BlueSuffix are comparing it to the libraries listed below
- β40Updated 3 months ago
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β45Updated 9 months ago
- β36Updated 9 months ago
- An implementation for MLLM oversensitivity evaluationβ13Updated 4 months ago
- A package that achieves 95%+ transfer attack success rate against GPT-4β17Updated 5 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ32Updated last year
- β32Updated 3 months ago
- β31Updated 8 months ago
- β43Updated 7 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β18Updated 5 months ago
- CVPR 2025 - Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Modelsβ14Updated 3 weeks ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacksβ13Updated last year
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ19Updated last year
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)β23Updated 4 months ago
- β41Updated last year
- Code for Transferable Unlearnable Examplesβ19Updated 2 years ago
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RLβ14Updated this week
- β19Updated 6 months ago
- β19Updated last month
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Modelsβ51Updated 11 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]β58Updated last year
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectorβ¦β24Updated 4 months ago
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"β16Updated last month
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β50Updated last week
- Code for Arxiv When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?β21Updated last month
- Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks"β11Updated 4 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"β44Updated 2 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β61Updated 2 months ago
- β11Updated last year
- Accepted by ECCV 2024β115Updated 5 months ago