XuankunRong / Awesome-LVLM-SafetyLinks
A curated list of resources dedicated to the safety of Large Vision-Language Models. This repository aligns with our survey titled A Survey of Safety on Large Vision-Language Models: Attacks, Defenses, and Evaluations.
β98Updated last month
Alternatives and similar repositories for Awesome-LVLM-Safety
Users that are interested in Awesome-LVLM-Safety are comparing it to the libraries listed below
Sorting:
- [ICLR 2024 Spotlight π₯ ] - [ Best Paper Award SoCal NLP 2023 π] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modalβ¦β56Updated last year
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as β¦β64Updated this week
- Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)β102Updated 2 months ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacksβ13Updated last year
- Accepted by ECCV 2024β130Updated 7 months ago
- β46Updated 6 months ago
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacksβ17Updated last month
- A package that achieves 95%+ transfer attack success rate against GPT-4β20Updated 7 months ago
- [CVPR2024] MMA-Diffusion: MultiModal Attack on Diffusion Modelsβ161Updated last year
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Modelsβ185Updated last week
- [NAACL 2025 Main] Official Implementation of MLLMU-Benchβ26Updated 2 months ago
- β26Updated 2 weeks ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shiβ¦β58Updated 10 months ago
- β22Updated 9 months ago
- A collection of resources on attacks and defenses targeting text-to-image diffusion modelsβ69Updated 2 months ago
- β34Updated 10 months ago
- [ECCV2024] Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectorβ¦β26Updated 6 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)β23Updated 7 months ago
- Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]β60Updated last year
- β43Updated 6 months ago
- [CVPR 2025] Official implementation for "Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreβ¦β20Updated last week
- An implementation for MLLM oversensitivity evaluationβ13Updated 6 months ago
- This is an official repository of ``VLAttack: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models'' (NeurIPS 2β¦β53Updated 2 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking β¦β28Updated 7 months ago
- Universal Adversarial Attack, Multimodal Adversarial Attacks, VLP models, Contrastive Learning, Cross-modal Perturbation Generator, Generβ¦β17Updated 7 months ago
- Implementation of BadCLIP https://arxiv.org/pdf/2311.16194.pdfβ20Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.β71Updated 4 months ago
- [CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Modelsβ130Updated 2 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Imagesβ35Updated last year
- Accepted by IJCAI-24 Survey Trackβ205Updated 9 months ago