Meta tags:
description=GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.;

Headings (most frequently used words):

this, repositories, saved, searches, navigation, to, your, topic, footer, easyjailbreak, search, code, users, issues, pull, requests, provide, feedback, llm, safety, benchmark, menu, use, filter, results, more, quickly, here, are, public, matching, improve, page, add, repo, babelscape, alert, billchan226, safewatch, declare, lab, resta, awsm, research, sealguard, kanson1996, livesecbench, sahil170595, huggingface, rtsi, beviah, fracture,

Text of the page (most frequently used words):
llm (28), safety (26), #benchmark (15), code (15), github (12), security (10), issues (10), your (9), python (9), pull (9), requests (9), star (9), updated (8), and (7), alignment (7), for (7), all (7), topic (6), evaluation (6), enterprise (6), view (6), you (5), this (5), 2026 (5), topics (5), models (5), search (5), community (4), with (4), the (4), red (4), jailbreak (4), language (4), use (4), explore (4), support (4), can (3), manage (3), navigation (3), more (3), page (3), add (3), testing (3), teaming (3), model (3), framework (3), mar (3), 2025 (3), video (3), alert (3), repositories (3), another (3), tab (3), window (3), refresh (3), session (3), reload (3), sign (3), saved (3), documentation (3), feedback (3), grade (3), features (3), copilot (3), platform (3), solutions (3), that (2), footer (2), learn (2), repository (2), repo (2), developers (2), feb (2), research (2), adversarial (2), detection (2), tools (2), huggingface (2), are (2), generate (2), livesecbench (2), multilingual (2), sealguard (2), software (2), 2024 (2), llms (2), through (2), lab (2), guardrail (2), official (2), safewatch (2), nlp (2), large (2), easyjailbreak (2), sponsors (2), events (2), collections (2), trending (2), signed (2), appearance (2), settings (2), cancel (2), see (2), available (2), searches (2), business (2), advanced (2), developer (2), open (2), source (2), resources (2), customer (2), services (2), devops (2), app (2), perform, action, time, not, share, personal, information, cookies, contact, docs, status, privacy, terms, inc, associate, visit, landing, select, curate, description, image, links, easily, about, improve, judge, prompt, injection, rlhf, team, discovering, failures, frontier, fracture, beviah, jun, quantsafe, certifier, whether, quantized, prone, jailbroken, unsafe, outputs, rtsi, sahil170595, engineering, 面向中文场景的大模型安全评测基准, 框架结合动态题库, 模型对战与客观评分流程, 可在伦理, 合法性, 事实性, 对抗鲁棒与推理安全等核心维度持续追踪模型表现, kanson1996, jul, guardrails, safeguarding, conversations, southeast, asian, languages, systems, awsm, benchmarking, algorithm, restore, fine, tuned, task, arithmetic, resta, declare, generation, iclr, implementation, efficient, policy, following, transparent, explanations, billchan226, sep, transformers, monitoring, bias, machine, learning, artificial, intelligence, paper, comprehensive, assessing, babelscape, discrete, optimization, easy, prompts, 871, here, public, matching, message, dismiss, switched, accounts, out, resetting, focus, create, qualifiers, our, query, name, filter, results, quickly, submit, include, email, address, contacted, read, every, piece, take, input, very, seriously, provide, syntax, tips, clear, users, jump, pricing, premium, ons, powered, archive, program, stars, accelerator, maintainer, programs, fund, partners, trust, center, forum, skills, insights, ebooks, reports, webinars, stories, type, development, industries, government, manufacturing, financial, healthcare, industry, cases, devsecops, modernization, case, nonprofits, startups, small, medium, teams, enterprises, company, size, marketplace, changelog, blog, why, stop, leaks, before, they, start, secret, protection, secure, build, find, fix, vulnerabilities, application, changes, review, plan, track, work, instant, dev, environments, codespaces, automate, any, workflow, actions, workflows, integrate, external, mcp, registry, new, direct, agents, from, issue, merge, write, better, creation, toggle, menu, skip, content,

Text of the page (random words):
llm safety benchmark github topics github skip to content navigation menu toggle navigation sign in appearance settings platform ai code creation github copilot write better code with ai github copilot app direct agents from issue to merge mcp registry new integrate external tools developer workflows actions automate any workflow codespaces instant dev environments issues plan and track work code review manage code changes application security github advanced security find and fix vulnerabilities code security secure your code as you build secret protection stop leaks before they start explore why github documentation blog changelog marketplace view all features solutions by company size enterprises small and medium teams startups nonprofits by use case app modernization devsecops devops ci cd view all use cases by industry healthcare financial services manufacturing government view all industries view all solutions resources explore by topic ai software development devops security view all topics explore by type customer stories events webinars ebooks reports business insights github skills support services documentation customer support community forum trust center partners view all resources open source community github sponsors fund open source developers programs security lab maintainer community accelerator github stars archive program repositories topics trending collections enterprise enterprise solutions enterprise platform ai powered developer platform available add ons github advanced security enterprise grade security features copilot for business enterprise grade ai features premium support enterprise grade 24 7 support pricing search or jump to search code repositories users issues pull requests search clear search syntax tips provide feedback we read every piece of feedback and take your input very seriously include my email address so i can be contacted cancel submit feedback saved searches use saved searches to filter your results more quickly name query to see all available qualifiers see our documentation cancel create saved search sign in sign up appearance settings resetting focus you signed in with another tab or window reload to refresh your session you signed out in another tab or window reload to refresh your session you switched accounts on another tab or window reload to refresh your session dismiss alert message explore topics trending collections events github sponsors llm safety benchmark star here are 8 public repositories matching this topic easyjailbreak easyjailbreak star 871 code issues pull requests an easy to use python framework to generate adversarial jailbreak prompts jailbreak discrete optimization large language model llm security llm safety benchmark jailbreak framework updated mar 30 2026 python babelscape alert star 60 code issues pull requests official repository for the paper alert a comprehensive benchmark for assessing large language models safety through red teaming nlp benchmark ai artificial intelligence nlp machine learning red teaming bias detection safety monitoring transformers models llm llm evaluation llm safety llm safety benchmark updated sep 20 2024 python billchan226 safewatch star 45 code issues pull requests iclr 2025 official implementation for safewatch an efficient safety policy following video guardrail model with transparent explanations video generation llm safety benchmark video guardrail updated feb 11 2025 python declare lab resta star 33 code issues pull requests restore safety in fine tuned language models through task arithmetic alignment safety alignment algorithm llm llms llm safety llms benchmarking llm safety benchmark updated mar 28 2024 python awsm research sealguard star 3 code issues pull requests sealguard safeguarding the multilingual conversations in southeast asian languages for llm software systems guardrails llm safety benchmark safety alignment multilingual safety alignment updated jul 12 2025 python kanson1996 livesecbench star 1 code issues pull requests livesecbench 面向中文场景的大模型安全评测基准 框架结合动态题库 模型对战与客观评分流程 可在伦理 合法性 事实性 隐私 对抗鲁棒与推理安全等核心维度持续追踪模型表现 benchmark ai safety ai engineering ai evaluation llm llm security llm evaluation llm safety benchmark updated mar 24 2026 python sahil170595 huggingface rtsi star 0 code issues pull requests quantsafe certifier for testing whether quantized models are prone to be jailbroken and generate unsafe outputs huggingface llm tools llm safety llm safety benchmark llm safety evaluation updated jun 15 2026 python beviah fracture star 0 code issues pull requests red team framework for discovering alignment failures in frontier language models model evaluation ai safety jailbreak detection red teaming rlhf prompt injection llm evaluation llm safety llm safety benchmark llm judge alignment testing adversarial testing alignment research updated feb 19 2026 python improve this page add a description image and links to the llm safety benchmark topic page so that developers can more easily learn about it curate this topic add this topic to your repo to associate your repository with the llm safety benchmark topic visit your repo s landing page and select manage topics learn more footer 2026 github inc footer navigation terms privacy security status community docs contact manage cookies do not share my personal information you can t perform that action at this time