{"data":{"node":{"slug":"parameterlab-trap","name":"trap","tagline":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","github_url":"https://github.com/parameterlab/trap","owner":"parameterlab","repo":"trap","owner_avatar_url":"https://avatars.githubusercontent.com/u/134953478?v=4","primary_language":"Jupyter Notebook","stars":15,"forks":1,"topics":["acl2024","adversarial-attacks","fingerprint","fingerprinting","large-language-models","llm","research"],"archived":false,"github_pushed_at":"2024-11-20T14:53:30+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/parameterlab-trap","markdown_url":"https://www.graphcanon.com/tools/parameterlab-trap.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/parameterlab-trap","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=parameterlab-trap"},"categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"acl2024","name":"acl2024"},{"slug":"adversarial-attacks","name":"adversarial-attacks"},{"slug":"fingerprinting","name":"fingerprinting"},{"slug":"large-language-models","name":"large language models"},{"slug":"research","name":"research"}],"edges":[],"neighbours":[{"slug":"lightning-ai-litgpt","name":"litgpt","tagline":"High-performance LLMs with recipes for pretraining, finetuning and deployment","github_url":"https://github.com/Lightning-AI/litgpt","owner":"Lightning-AI","repo":"litgpt","owner_avatar_url":"https://avatars.githubusercontent.com/u/58386951?v=4","primary_language":"Python","stars":13605,"forks":1483,"topics":["ai","artificial-intelligence","deep-learning","large-language-models","llm","llm-inference","llms"],"archived":false,"github_pushed_at":"2026-07-20T10:24:12+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/lightning-ai-litgpt","markdown_url":"https://www.graphcanon.com/tools/lightning-ai-litgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lightning-ai-litgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lightning-ai-litgpt","shared_categories":["llm-frameworks"]},{"slug":"llm-attacks-llm-attacks","name":"llm-attacks","tagline":"Universal and Transferable Attacks on Aligned Language Models","github_url":"https://github.com/llm-attacks/llm-attacks","owner":"llm-attacks","repo":"llm-attacks","owner_avatar_url":"https://avatars.githubusercontent.com/u/140664770?v=4","primary_language":"Python","stars":4756,"forks":633,"topics":[],"archived":false,"github_pushed_at":"2024-08-02T06:02:18+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/llm-attacks-llm-attacks","markdown_url":"https://www.graphcanon.com/tools/llm-attacks-llm-attacks.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/llm-attacks-llm-attacks","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=llm-attacks-llm-attacks","shared_categories":["evaluation-observability","llm-frameworks"]},{"slug":"cyberark-fuzzyai","name":"FuzzyAI","tagline":"A tool for automated LLM fuzzing to detect and mitigate jailbreaks","github_url":"https://github.com/cyberark/FuzzyAI","owner":"cyberark","repo":"FuzzyAI","owner_avatar_url":"https://avatars.githubusercontent.com/u/30869256?v=4","primary_language":"Jupyter Notebook","stars":1543,"forks":214,"topics":["ai","ai-red-team","fuzzing","jailbreak","jailbreaking","llm","llm-evaluation","llm-security","llms","security"],"archived":false,"github_pushed_at":"2026-02-06T21:59:21+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/cyberark-fuzzyai","markdown_url":"https://www.graphcanon.com/tools/cyberark-fuzzyai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/cyberark-fuzzyai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=cyberark-fuzzyai","shared_categories":["evaluation-observability"]},{"slug":"sherdencooper-gptfuzz","name":"GPTFuzz","tagline":"Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","github_url":"https://github.com/sherdencooper/GPTFuzz","owner":"sherdencooper","repo":"GPTFuzz","owner_avatar_url":"https://avatars.githubusercontent.com/u/37368657?v=4","primary_language":"Python","stars":604,"forks":87,"topics":[],"archived":false,"github_pushed_at":"2026-02-27T17:19:03+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/sherdencooper-gptfuzz","markdown_url":"https://www.graphcanon.com/tools/sherdencooper-gptfuzz.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sherdencooper-gptfuzz","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sherdencooper-gptfuzz","shared_categories":["evaluation-observability","llm-frameworks"]},{"slug":"deadbits-vigil-llm","name":"vigil-llm","tagline":"Detect prompt injections and other risky inputs in LLMs","github_url":"https://github.com/deadbits/vigil-llm","owner":"deadbits","repo":"vigil-llm","owner_avatar_url":"https://avatars.githubusercontent.com/u/1332757?v=4","primary_language":"Python","stars":496,"forks":56,"topics":["adversarial-attacks","adversarial-machine-learning","large-language-models","llm-security","llmops","prompt-injection","security-tools","yara-scanner"],"archived":false,"github_pushed_at":"2024-01-31T18:43:41+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/deadbits-vigil-llm","markdown_url":"https://www.graphcanon.com/tools/deadbits-vigil-llm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/deadbits-vigil-llm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=deadbits-vigil-llm","shared_categories":["evaluation-observability"]},{"slug":"liu00222-open-prompt-injection","name":"Open-Prompt-Injection","tagline":"Benchmark and toolkit for prompt injection attacks and defenses in LLMs","github_url":"https://github.com/liu00222/Open-Prompt-Injection","owner":"liu00222","repo":"Open-Prompt-Injection","owner_avatar_url":"https://avatars.githubusercontent.com/u/42081599?v=4","primary_language":"Python","stars":470,"forks":74,"topics":["llm","llm-security","llms","prompt-injection","prompt-injection-tool","security-and-privacy"],"archived":false,"github_pushed_at":"2025-10-29T17:11:34+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/liu00222-open-prompt-injection","markdown_url":"https://www.graphcanon.com/tools/liu00222-open-prompt-injection.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/liu00222-open-prompt-injection","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=liu00222-open-prompt-injection","shared_categories":["evaluation-observability","llm-frameworks"]},{"slug":"ddzipp-autoaudit","name":"AutoAudit","tagline":"LLM for Cyber Security","github_url":"https://github.com/ddzipp/AutoAudit","owner":"ddzipp","repo":"AutoAudit","owner_avatar_url":"https://avatars.githubusercontent.com/u/87225910?v=4","primary_language":"HTML","stars":354,"forks":38,"topics":["cyber-security","fine-tuning","gpt","llama","lora","qlora","security-tools"],"archived":false,"github_pushed_at":"2025-02-28T10:55:21+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/ddzipp-autoaudit","markdown_url":"https://www.graphcanon.com/tools/ddzipp-autoaudit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ddzipp-autoaudit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ddzipp-autoaudit","shared_categories":["evaluation-observability"]},{"slug":"unispac-visual-adversarial-examples-jailbreak-large-language-models","name":"Visual-Adversarial-Examples-Jailbreak-Large-Language-Models","tagline":"Repository for visual adversarial examples that jailbreak large language models","github_url":"https://github.com/Unispac/Visual-Adversarial-Examples-Jailbreak-Large-Language-Models","owner":"Unispac","repo":"Visual-Adversarial-Examples-Jailbreak-Large-Language-Models","owner_avatar_url":"https://avatars.githubusercontent.com/u/45935569?v=4","primary_language":"Python","stars":282,"forks":30,"topics":[],"archived":false,"github_pushed_at":"2024-05-13T05:36:24+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/unispac-visual-adversarial-examples-jailbreak-large-language-models","markdown_url":"https://www.graphcanon.com/tools/unispac-visual-adversarial-examples-jailbreak-large-language-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/unispac-visual-adversarial-examples-jailbreak-large-language-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=unispac-visual-adversarial-examples-jailbreak-large-language-models","shared_categories":[]},{"slug":"tmlr-group-deepinception","name":"DeepInception","tagline":"Develops techniques to influence large language model behavior","github_url":"https://github.com/tmlr-group/DeepInception","owner":"tmlr-group","repo":"DeepInception","owner_avatar_url":"https://avatars.githubusercontent.com/u/102131272?v=4","primary_language":"Python","stars":177,"forks":19,"topics":["deep","gpt","gpt3","gpt4","inception","jailbreak","large-language-models","llm","safety","trustworthy"],"archived":false,"github_pushed_at":"2024-02-20T03:54:41+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/tmlr-group-deepinception","markdown_url":"https://www.graphcanon.com/tools/tmlr-group-deepinception.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tmlr-group-deepinception","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tmlr-group-deepinception","shared_categories":["llm-frameworks"]},{"slug":"njunlp-renellm","name":"ReNeLLM","tagline":"Implementation of generalized nested jailbreak prompts targeting large language models.","github_url":"https://github.com/NJUNLP/ReNeLLM","owner":"NJUNLP","repo":"ReNeLLM","owner_avatar_url":"https://avatars.githubusercontent.com/u/31466622?v=4","primary_language":"Python","stars":163,"forks":17,"topics":[],"archived":false,"github_pushed_at":"2025-09-02T09:32:44+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/njunlp-renellm","markdown_url":"https://www.graphcanon.com/tools/njunlp-renellm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/njunlp-renellm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=njunlp-renellm","shared_categories":["evaluation-observability"]},{"slug":"safellama-plexiglass","name":"plexiglass","tagline":"A toolkit for detecting and protecting against vulnerabilities in Large Language Models (LLMs).","github_url":"https://github.com/safellama/plexiglass","owner":"safellama","repo":"plexiglass","owner_avatar_url":"https://avatars.githubusercontent.com/u/141878442?v=4","primary_language":"Python","stars":153,"forks":18,"topics":["adversarial-attacks","adversarial-machine-learning","cybersecurity","deep-learning","deep-neural-networks","machine-learning","security"],"archived":false,"github_pushed_at":"2026-02-04T22:18:58+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/safellama-plexiglass","markdown_url":"https://www.graphcanon.com/tools/safellama-plexiglass.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/safellama-plexiglass","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=safellama-plexiglass","shared_categories":["evaluation-observability"]},{"slug":"microsoft-bipia","name":"BIPIA","tagline":"Benchmark for evaluating LLM robustness to indirect prompt injection attacks.","github_url":"https://github.com/microsoft/BIPIA","owner":"microsoft","repo":"BIPIA","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"Python","stars":149,"forks":19,"topics":["llm-security"],"archived":false,"github_pushed_at":"2024-04-15T02:08:17+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/microsoft-bipia","markdown_url":"https://www.graphcanon.com/tools/microsoft-bipia.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-bipia","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-bipia","shared_categories":["evaluation-observability"]}]}}