☆21Oct 25, 2024Updated 2 years ago
Alternatives and similar repositories for SafeBench
Users that are interested in SafeBench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2025] PyTorch Implementation of "ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time"☆34Jul 20, 2025Updated last year
- ☆13Sep 29, 2025Updated last year
- Accepted by ECCV 2024☆221Oct 15, 2024Updated 2 years ago
- ☆62Jun 5, 2024Updated 2 years ago
- The first toolkit for MLRM safety evaluation, providing unified interface for mainstream models, datasets, and jailbreaking methods!☆15Apr 8, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆91Jan 19, 2025Updated last year
- ☆11Oct 13, 2025Updated last year
- ☆12Oct 30, 2024Updated 2 years ago
- The reinforcement learning codes for dataset SPA-VL☆48Jun 24, 2024Updated 2 years ago
- ☆34Mar 16, 2025Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆43Oct 17, 2024Updated 2 years ago
- ☆86Mar 30, 2025Updated last year
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆46Apr 21, 2024Updated 2 years ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆37Dec 30, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆39Oct 23, 2024Updated 2 years ago
- ☆46Jun 19, 2025Updated last year
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆177Jun 27, 2025Updated last year
- We introduce Multi-P2A, a Multi-perspective Privacy Assessment aimed at evaluating privacy risks of LVLMs comprehensively.☆13Sep 23, 2026Updated last month
- Accept by CVPR 2025 (highlight)☆27Jun 8, 2025Updated last year
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆39Nov 2, 2024Updated 2 years ago
- Röttger et al. (2025): "MSTS: A Multimodal Safety Test Suite for Vision-Language Models"☆21Mar 31, 2025Updated last year
- [ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".☆182Aug 11, 2026Updated 3 months ago
- 联邦学习安全聚合代码☆13Jul 20, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [NeurIPS 2025] An official source code for paper "GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning".☆125Feb 22, 2026Updated 8 months ago
- Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence☆39Jul 31, 2025Updated last year
- ☆27Mar 17, 2025Updated last year
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆32Nov 2, 2025Updated last year
- ☆135Jul 29, 2026Updated 3 months ago
- Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding.☆13Nov 19, 2024Updated 2 years ago
- [NeurIPS 2025] Official Implementation for "Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding"☆23Dec 8, 2024Updated last year
- Revisiting Character-level Adversarial Attacks for Language Models, ICML 2024☆20Aug 28, 2026Updated 2 months ago
- [AISTATS 2025] Official implementation of "Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting"☆17Apr 30, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆95Jun 6, 2024Updated 2 years ago
- A working Python implementation of a Secure Aggregation protocol adapted from ”Practical Secure Aggregation for Privacy-Preserving Machin…☆13Sep 28, 2024Updated 2 years ago
- [AAAI25] Official Repo of Paper `ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates`☆14Mar 22, 2025Updated last year
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆38Jun 23, 2025Updated last year
- [USENIX Security'24] Official repository of "Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise a…☆120Oct 11, 2024Updated 2 years ago
- ☆30Jun 5, 2024Updated 2 years ago
- [EMNLP 2025] Official code for the paper "SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning"☆16May 12, 2026Updated 6 months ago
Are these results useful?