VOOZH

URL: https://github.com/topics/adversarial-ai

⇱ adversarial-ai · GitHub Topics · GitHub

#

adversarial-ai

Here are 41 public repositories matching this topic...

codexstar69 / bug-hunter

Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.

opencode devtools vscode multi-agent code-quality cursor security-scanner claude bug-detection github-copilot auto-fix llm ai-code-review claude-code codex-cli coding-agent adversarial-ai kiro pi-coding-agent

Updated
JavaScript

👁 Worm-GPT-LLM-2026

dubermandeer / Worm-GPT-LLM-2026

High-performance C++ execution engine for LLM red-teaming and prompt engineering. Deploy dynamic jailbreak payloads, bypass alignment guardrails, and utilize free autonomous uncensored conversational logic locally.

machine-learning cybersecurity penetration-testing ethical-hacking ai-safety vulnerability-scanner red-teaming cpp-framework token-manipulation prompt-engineering prompt-injection jailbreak-prompt uncensored-llm llama-3 adversarial-ai worm-gpt blackhat-gpt llm-jailbreak openai-bypass dark-llm

Updated
C++

regaan / basilisk

Basilisk — Open-source AI red teaming framework with genetic prompt evolution. Automated LLM security testing for GPT-4, Claude, Grok, Gemini. OWASP LLM Top 10 coverage. 32 attack modules.

security ai jailbreak genetic-algorithm owasp pentesting offensive-security red-team vulnerability-scanner red-teaming ai-security basilisk llm prompt-injection llm-security owasp-llm-top-10 ai-red-teaming adversarial-ai llm-security-compliance-prompt-injection chatgpt-security

Updated
Python

fallen-angel-systems / fas-judgement-oss

Open-source prompt injection attack console. Test AI security by firing categorized attacks at any endpoint.

game python cli owasp cybersecurity penetration-testing gamification ctf capture-the-flag security-training red-team machine-learning-security ai-security prompt-injection llm-security adversarial-ai

Updated
Python

obscuralabs-AI / Symbolic-Prompt-PenTest

Semantic Stealth Attacks & Symbolic Prompt Red Teaming on GPT and other LLMs.

prompt-engineering ai-penetration-testing adversarial-ai llm-red-teaming symbolic-prompt gpt4-security obscuralabs

Updated

karloks2005 / JailbreakLab

Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial attacks with a web-based interactive lab.

react docker kubernetes jailbreak model-alignment machine-learning-security ai-security fastapi huggingface prompt-injection llm-security llm-safety security-research-tool ai-evaluation-framework adversarial-ai prompt-defense llm-red-teaming

Updated
Python

SnailSploit / AATMF-Adversarial-AI-Threat-Modeling-Framework

AATMF | An Open Source - Adversarial AI Threat Modeling Framework

owasp threat-modeling penetration-testing-framework redteaming ai-security mitre-atlas generative-ai llm-security adversarial-ai aatmf

Updated
YARA

URDev4ever / LATT

LLM Attack Testing Toolkit is a structured methodology and mindset framework for testing Large Language Model (LLM) applications against logic abuse, prompt injection, jailbreaks, and workflow manipulation.

offensive-security security-research prompt-injection llm-security agent-security ai-red-teaming adversarial-ai rag-security llm-pentesting tool-injection jailbreak-testing logic-abuse ai-workflow-testing context-leakage ai-application-security

Updated

TheApexWu / crucible

1st Place Winner (General Judge) - Datadog Self-Improving Agents Hack. Two identical AI agents play Split or Steal. No pre-programmed betrayal. They discover deception on their own. Built with @evancorrea.

datadog multi-agent gemini game-theory emergent-behavior hackathon-winner llm elevenlabs braintrust adversarial-ai split-or-steal

Updated
Python

bchtitihi / legacy-audit-agents

Audit legacy codebases with adversarial AI agent teams — 7 iterations, 168 findings, 81.8% reliability score

methodology ai-agents legacy-code claude code-audit anthropic claude-code agent-teams adversarial-ai

Updated

jasoncobra3 / LLM_Sentinel

LLM Sentinel Red Teaming Platform is an enterprise-grade framework for automated security testing of Large Language Models, detecting vulnerabilities such as jailbreaks, prompt injection, and system prompt leakage across multiple providers, with structured attack orchestration, risk scoring, and security reporting to harden models before production

openai ai-safety ai-security rag azure-openai large-language-models generative-ai langchain prompt-injection anthropic llm-security multi-llm llm-evaluation genai-security ai-security-tool adversarial-ai llm-red-teaming model-security jailbreak-testing

Updated
Python

scthornton / Chain-of-Thought-Reasoning-Attacks

Breaking Chain-of-Thought: A Comprehensive Taxonomy of Reasoning Vulnerabilities in Production AI Systems

jailbreak jupyter-notebook security-research ai-security chain-of-thought prompt-injection llm-security adversarial-ai

Updated
Jupyter Notebook

khanovico / prompt-guard

🛡️ Enterprise-grade AI security framework protecting LLMs from prompt injection attacks using ML-powered detection

python machine-learning mongodb cybersecurity faiss ai-security huggingface prompt-injection ai-protection llm-security prompt-security adversarial-ai

Updated
Python

daletoniris / security-talks

Slides and materials from cybersecurity talks at Chubut Hack (2021-2022)

talks presentations cybersecurity infosec wardriving adversarial-ai chubut-hack

Updated

tomaszgy / cherchoux

Stateful multi-agent system for adversarial hypothesis testing in biomedical research.

python scientific-computing multi-agent-systems rag biomedical-research research-automation llm-agents langgraph adversarial-ai

Updated
Python

xCenny / Whusdata

python conflict-resolution multi-agent dataset-generation reasoning synthetic-data fine-tuning sft huggingface streamlit rlhf llm-training adversarial-ai

Updated
Python

annoeyed / MA_BLR

A research framework for simulating, detecting, and defending against backdoor loop attacks in LLM-based multi-agent systems.

cybersecurity multi-agent-systems red-teaming ai-security backdoor-attacks large-language-models llm-security adversarial-ai python-simulation-framework

Updated
Python

ZyluxXD / zerobypass

Proof of concept tool to bypass document replay technology (such as GPTZero).

python proof-of-concept poc ai-detection-bypasser llm-detection adversarial-ai

Updated
Python

NovasPlace / Autonomic_Core

Autonomic substrate for AI agents. Decentralized immune system to prevent semantic drift.

immune-system adversarial-ai agent-safety autonomic

Updated
Python

DUBSOpenHub / havoc-hackathon

Pit AI models against each other. Score them sealed. Crown a winner. All built using the GitHub Copilot CLI. ⚡

orchestration multi-agent multi-model ai-agents prompt-engineering copilot-cli copilot-extensions adversarial-ai blind-adjudication

Updated
Python

Improve this page

Add a description, image, and links to the adversarial-ai 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 adversarial-ai topic, visit your repo's landing page and select "manage topics."

You can’t perform that action at this time.