Mechanism-grounded taxonomy of 40 LLM jailbreak patterns across 10 categories. 8,000-trial bootstrap evaluation for the June 2026 frontier (Claude Opus 4-8, GPT-5.5, Gemini 3.5, DeepSeek V4). Every citation direct-WebFetch verified; refuted claims documented.
☆20Aug 22, 2026Updated 2 months ago
Alternatives and similar repositories for llm-jailbreak-taxonomy
Users that are interested in llm-jailbreak-taxonomy are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- VulnerAIble/VulnAI - Deploy your own vulnerable AI application and learn how to secure it.☆11Jul 21, 2025Updated last year
- Application Security Mind Maps☆12Apr 10, 2021Updated 5 years ago
- Interactive 30/60/90-day study tracker for the HTB Certified Offensive AI Expert (COAE) certification.☆15May 24, 2026Updated 5 months ago
- [ICML 2025] Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions☆16Mar 7, 2026Updated 8 months ago
- Security scanner for MCP servers. Every finding carries its evidence, including the server's actual response bytes.☆12Sep 4, 2026Updated 2 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Methodology and tooling for crafting model-specific jailbreak system prompts from alignment fingerprints.☆19Sep 27, 2026Updated last month
- Open Agent Security Benchmark - 223 attack scenarios, product-agnostic adapter interface, MITRE ATLAS mapped☆10Nov 7, 2026Updated last week
- Cloud security audit tools for AI agents — AWS, Azure, GCP misconfiguration detection via MCP. 38 tools, 60+ checks. The agent finds vuln…☆23Mar 14, 2026Updated 7 months ago
- Scriptset to enumerate PCIe Device to NUMA mapping within an VMware ESXi Host☆11Jan 10, 2020Updated 6 years ago
- ☆12Nov 30, 2025Updated 11 months ago
- Kuintessence is an advanced computing orchestration system designed to revolutionize HPC workload and cluster management, to empower HPC …☆13Mar 20, 2024Updated 2 years ago
- Official inference code for C-SafeQA, a policy-grounded benchmark for response-level Chinese safety evaluation of LLMs and automated safe…☆24Nov 2, 2026Updated last week
- Security layer for AI agent-to-agent communication. Every message is signed, inspected, and logged. If it doesn't comply, it doesn't pass…☆19Sep 18, 2026Updated last month
- A safety evaluation framework for agents.☆15Jul 23, 2026Updated 3 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.
- FAST 22☆12Jul 18, 2022Updated 4 years ago
- ☆14Jan 12, 2022Updated 4 years ago
- HOP 3.0 — HopSpec task-spec language + HopJIT execution engine for LLM agents☆26Oct 12, 2026Updated last month
- Jupyter Kernel Protocol for rust☆14May 5, 2026Updated 6 months ago
- A local, rule-based security guard for DeepSeek Harness agents. It hooks agent tool calls and prompt assembly and applies a policy table …☆26Sep 17, 2026Updated last month
- CVE-2026-126187 Unauthenticated RCE in React Server Components - PoC and Docker lab for GHSA-xqc2-xf4c-x3h3 / GHSA-673q-mjm6-r5xr☆32Updated this week
- Official Code for Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification.☆22Jul 1, 2026Updated 4 months ago
- ☆17Oct 28, 2026Updated 2 weeks ago
- Tiny recursive descent expression parser, compiler, and evaluation engine for math expressions.☆11Jul 11, 2023Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A framework for agent to agent authentication using existing standards like WIMSE, OAuth and SPIFFE☆23Updated this week
- Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI☆39Updated this week
- modified mdb for examining zfs on disk☆21Aug 12, 2013Updated 13 years ago
- SafeHarness: Security-Aware Harness Architecture for Safe AI Agent Deployment☆18May 12, 2026Updated 6 months ago
- Proof-only PoC for CVE-2026-98432 (Linux IPv4/TCP ireq_opt use-after-free): race trigger, heap-reuse oracle, no code execution☆31Oct 30, 2026Updated 2 weeks ago
- Camera Ready copy of FuzzSlice v1 code for ICSE☆20Jan 22, 2024Updated 2 years ago
- SPECjvm2008 Benchmark Suite☆20Jan 22, 2016Updated 10 years ago
- CLI tool to manipulate URLs☆18Nov 27, 2023Updated 2 years ago
- Cozely: a simple framework for making games in Go☆13Mar 5, 2019Updated 7 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Emulator for Zachtronics TIS100 written in C#☆11Jul 10, 2015Updated 11 years ago
- 日志服务（SLS）案例中心☆31Updated this week
- oVirt 中文版文档☆26Nov 16, 2014Updated 11 years ago
- Apple I BASIC, partially reverse-engineered source code☆14Aug 26, 2020Updated 6 years ago
- DTGO (灯塔狩猎者) 是一个用于批量管理和监控资产灯塔系统任务的图形化工具。它能够自动发现灯塔系统、批量提交任务、监控任务状态，并支持导出任务结果。☆36Feb 10, 2025Updated last year
- Alice 集成技能包 · 放进去就能用 · Drop-in skill suite for AI coding agents☆63Sep 29, 2026Updated last month
- [TIP 2026] Toward Generalizable Forgery Detection and Reasoning.☆26Apr 20, 2026Updated 6 months ago
Are these results useful?