Shark Family is an AI safety red-teaming and jailbreak attack module. it harnesses powerful optimization and automated strategies to generate highly effective jailbreak prompts that penetrate diverse model defenses for extreme stress testing. | 鲨鱼家族 是一个 AI 安全红队与越狱攻击组件。它利用强大的优化能力与自动化策略,生成极具穿透力的越狱指令,击破多种模型防御,为极限压力测试提供最强“利矛”。
☆15Oct 19, 2025Updated last year
Alternatives and similar repositories for Shark-Family
Users that are interested in Shark-Family are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The Oyster series is a set of safety models developed in-house by Alibaba-AAIG, devoted to building a responsible AI ecosystem. | Oyster …☆65Apr 29, 2026Updated 6 months ago
- A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack–Defense Evaluation☆80May 8, 2026Updated 6 months ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆91Feb 26, 2025Updated last year
- This is the official repository for Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models.☆17Jan 16, 2025Updated last year
- 轻量级 AI API 中转网关:统一管理多家上游 Key,提供 6 种负载均衡、失败自动切换、多维限流、响应缓存、额度监控与 Web 控制台。可在 Termux / Linux 直接运行,兼容 OpenAI 协议。☆13Oct 31, 2026Updated 2 weeks 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.
- Telegram信息收集情报平台☆28Sep 2, 2025Updated last year
- The Strata-Sword is a hierarchical Chinese-English jailbreak safety benchmark based on quantified reasoning complexity, developed in-hous…☆21Sep 3, 2025Updated last year
- AIDE PLUS(AIDE+) 基于官方的NDK安装脚本☆14May 25, 2026Updated 5 months ago
- Prompt Generator model for Stable Diffusion Models☆12Jun 20, 2023Updated 3 years ago
- DeepSeek Harness 插件市场导航站☆25Updated this week
- ☆10Dec 8, 2022Updated 3 years ago
- 通过ssrf漏洞对redis资产进行getshell的常见姿势☆10Aug 26, 2025Updated last year
- This repo is the official implementation of “Are Your Agents Upward Deceivers?”. The paper is accepted by ICML 2026.☆24Dec 15, 2025Updated 11 months ago
- IP探针链接生成器:确认在意之人是否平安的定位探针系统(PHP+MySQL 后端,Kotlin/Compose 客户端)☆15Sep 28, 2026Updated last month
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- New "Brash" Exploit Crashes Chromium Browsers Instantly with a Single Malicious URL☆12Oct 31, 2025Updated last year
- ☆11Oct 13, 2025Updated last year
- ☆11Jun 6, 2025Updated last year
- smplify code for point cloud based HMR☆10Jan 11, 2022Updated 4 years ago
- Backdoor Collection 👾☆14Updated this week
- A repo for code review sessions at CAS☆35Nov 19, 2024Updated last year
- 信息收集工具 对目标机器上的文档进行收集并打包☆13Jun 20, 2025Updated last year
- My presentation slides☆18Oct 31, 2025Updated last year
- AutoPPT — AI-Powered Interactive Lecture Slides Generator | AI备课神器 | 一键生成一整周精美、可交互的课件!☆57Nov 2, 2026Updated 2 weeks 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.
- 🧑🚀 全世界最好的LLM资料总结(语音视频生成、Agent、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.☆10Jul 28, 2025Updated last year
- PhantomHarvest 是一个隐蔽的后渗透传输软件,专为红队评估和安全研究设计。它能够从目标系统中提取敏感信息,并支持隐蔽的本地保存或远程传输。☆11Nov 27, 2025Updated 11 months ago
- ICCV 2025 official implementation for Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-b…☆13Jul 22, 2025Updated last year
- ☆12Oct 30, 2024Updated 2 years ago
- 隐藏 Gotohttp,实现轻量无痕远控☆11Nov 3, 2025Updated last year
- ☆34Mar 16, 2025Updated last year
- ☆13Sep 19, 2025Updated last year
- Adapted signed distance function (SDF) for detecting collisions between 3D interacting hands.☆15Mar 16, 2022Updated 4 years ago
- ocean ctf 管理后台☆11Mar 5, 2026Updated 8 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆13Sep 29, 2025Updated last year
- Official implementation of NeurIPS 2025 paper "Visual Instruction Bottleneck Tuning"☆15Apr 10, 2026Updated 7 months ago
- 基于 CVE-2025-55182 漏洞检测 burpsuite 被动扫描插件☆12Dec 5, 2025Updated 11 months ago
- This project provides a data set with bounding boxes, body poses, 3D face meshes & captions of people from our LAION-2.2B. Additionally i…☆14Jan 2, 2022Updated 4 years ago
- 本书为《C++17 the complete guide》的个人中文翻译,仅供学习和交流使用,侵删☆11Oct 28, 2020Updated 6 years ago
- 一款基于ChatGPT开发的,使用360Quake,Gemini,AWVS等工具的红队信息收集/攻击面/漏洞/AI分析系统☆11Dec 8, 2025Updated 11 months ago
- ECSO (Make MLLM safe without neither training nor any external models!) (https://arxiv.org/abs/2403.09572)☆39Nov 2, 2024Updated 2 years ago
Are these results useful?