EvoSynth is a SOTA automated LLM red-teaming framework that evolves executable, code-level jailbreak attack methods using multi-agent synthesis, evolutionary search, and self-correction.
☆60Feb 4, 2026Updated 7 months ago
Alternatives and similar repositories for EvoSynth
Users that are interested in EvoSynth are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PIPMN☆22Oct 10, 2024Updated last year
- ☆67May 21, 2025Updated last year
- ☆31Feb 19, 2025Updated last year
- A guard model for Agent☆41Jul 15, 2026Updated last month
- ☆32Jun 13, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Open-source red teaming framework for MLLMs with 42+ attack methods☆266Jul 17, 2026Updated last month
- [ICLR 2025] BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks☆31Nov 2, 2025Updated 10 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆34Dec 30, 2024Updated last year
- [ArXiv 2025] Imperceptible Jailbreaking against Large Language Models☆25Oct 7, 2025Updated 10 months ago
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆18Jul 11, 2025Updated last year
- Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University☆163Jul 10, 2026Updated last month
- ☆15Jun 22, 2026Updated 2 months ago
- [ICML 2026] RA-Det: Robustness Asymmetry Detection for AI-Generated Images☆17Mar 3, 2026Updated 6 months ago
- ECCV2024: Adversarial Prompt Tuning for Vision-Language Models☆31Mar 7, 2026Updated 5 months ago
- 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.
- PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses(COLM 2026)☆28Aug 27, 2026Updated last week
- Official implementation of "TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards"☆32Jul 20, 2026Updated last month
- Repository for 2030 project☆15Dec 29, 2025Updated 8 months ago
- [ICML 2026] Official implementation for paper "Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Ag…☆35Jul 31, 2026Updated last month
- [🏆ECCV'26] Official Repo for SlowBA: An efficiency backdoor attack towards VLM-based GUI agents☆18Updated this week
- The Official Repository for Paper "HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?"☆16May 2, 2026Updated 4 months ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆30Jun 1, 2026Updated 3 months ago
- [CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.☆3,766Aug 18, 2026Updated 2 weeks ago
- 🌱 SeedWorld — Plant a world. Watch it grow. An emergent world simulation engine powered by LLM. 给LLM一个世界设定,看它自己长出文明☆417Apr 3, 2026Updated 5 months ago
- 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.
- Replace coding puzzles with real-work simulations.☆1,906Aug 26, 2026Updated last week
- Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.☆2,441Aug 17, 2026Updated 2 weeks ago
- Open database of system prompts extracted from frontier LLMs using JustAsk☆41Apr 4, 2026Updated 5 months ago
- next easy report☆470Dec 29, 2025Updated 8 months ago
- AI for JDK1.8☆28Mar 21, 2026Updated 5 months ago
- ☆12Mar 24, 2023Updated 3 years ago
- The official code of [ICLR 2026] TFPI: Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient …☆103Jan 27, 2026Updated 7 months ago
- TVM Documentation in Chinese Simplified / TVM 中文文档☆3,928May 20, 2026Updated 3 months ago
- ShutterMuse, a open-sourced MLLM that provides both photographpher-side and subject-side guidance.☆103Aug 22, 2026Updated last week
- 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.
- The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.☆15Dec 16, 2024Updated last year
- Official code for our paper "SoK: Large Language Model Copyright Auditing via Fingerprinting"☆19Dec 31, 2025Updated 8 months ago
- LeakyCLIP is a CLIP inversion and privacy auditing framework for extracting training data signals from CLIP embeddings and analyzing memb…☆27Feb 27, 2026Updated 6 months ago
- 本项目是一个基于 Golang Gin 框架 开发的 B2C 电商平台，采用 MVC（Model-View-Controller）架构 进行模块化设计，能够扩展为实现前后端分离，支持后台商品管理、用户系统、订单交易、支付集成、数据分析等功能,系统地展…☆1,080Oct 12, 2025Updated 10 months ago
- [NeurIPS 2025] Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack☆15Nov 19, 2025Updated 9 months ago
- LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505☆4,090Jun 16, 2026Updated 2 months ago
- ExcelManus - AI-powered Excel Agent☆29Mar 6, 2026Updated 5 months ago