#

adversarial-ml

Here are 20 public repositories matching this topic...

AmirhosseinHonardoust / Noise-Injection-Techniques

Noise Injection Techniques provides a comprehensive exploration of methods to make machine learning models more robust to real-world bad data. This repository explains and demonstrates Gaussian noise, dropout, mixup, masking, adversarial noise, and label smoothing, with intuitive explanations, theory, and practical code examples.

Updated Nov 15, 2025

AI-Security-Research-Group / LLM-Attacks

Comprehensive taxonomy of AI security vulnerabilities, LLM adversarial attacks, prompt injection techniques, and machine learning security research. Covers 71+ attack vectors including model poisoning, agentic AI exploits, and privacy breaches.

machine-learning ai-security ai-privacy open-source-security adversarial-ml prompt-injection ai-red-teaming model-poisoning llm-attacks ai-vulnerabilities security-taxonomy

Updated Sep 19, 2025

tobias1248 / INCITE

Master's students in NCCU SoSLab maintaining a cleaned and restructured version of INCITE (based on PyCT).

cnn transformer mit-license neuronal-network concolic-testing adversarial-ml

Updated Dec 30, 2025
Python

donbaudin / meta-ai-bug-bounty

Bug bounty report demonstrating prompt injection and command execution vulnerabilities in Meta AI's Instagram Group Chat

cybersecurity penetration-testing bug-bounty ethical-hacking responsible-disclosure security-research mitre-attack red-teaming ai-security ai-risk adversarial-ml mitre-atlas prompt-injection meta-ai llm-vulnerabilities

Updated May 31, 2025

ParraX123 / meta-ai-bug-bounty

🛡️ Discover and analyze critical vulnerabilities in Meta AI's Instagram Group Chat, ensuring robust security through comprehensive testing and reporting.

cybersecurity penetration-testing ethical-hacking responsible-disclosure security-research mitre-attack red-teaming ai-security ai-risk adversarial-ml mitre-atlas prompt-injection meta-ai llm-vulnerabilities

Updated Dec 30, 2025

SecureAI-Team / awesome-aisecurity

A curated list of awesome resources for AI system security.

awesome enhancements good-first-issue ai-security mlsec adversarial-ml llm-security genai-security

Updated Dec 2, 2025

manasa-26 / Adversarial-ML-Scanner

Adversarial ML Scanner for threat detection and ML backdoor attcaks

code-injection adversarial-machine-learning adversarial-attacks threat-detection backdoor-attacks pii-detection ml-backdoors adversarial-ml adversarial-ml-in-security threat-scan adversial-scanner

Updated Feb 18, 2025
Python

hah23255 / security-vulnerabilities-cli-llm

Security Vulnerabilities and Defensive Mechanisms in CLI/Terminal-Based Large Language Model Deployments - A Comprehensive Research Synthesis (Technical Report, November 2025)

security cybersecurity arxiv research-paper machine-learning-security ai-security adversarial-ml prompt-injection llm-security cli-security

Updated Nov 19, 2025
Rich Text Format

rudra-swnt-12 / llm_court

Autonomous adversarial agents that debate and debug code before you see it.

fastapi groq adversarial-ml langgraph agentic-ai llama-4 gpt-oss-120b gpt-oss-20b

Updated Dec 6, 2025
Python

Lizzard1123 / Intro_to_ML_Safety

Fork for my contributions on Trojans, Comprehensive course materials covering ML safety, robustness, and AI alignment

documentation machine-learning course-materials educational ai-alignment adversarial-ml ai-saftey

Updated Aug 27, 2022

Shadowroot

Nathan-Luevano / Shadowroot

An experiment in backdooring a shell safety classifier by planting a hidden trigger in its training data.

python linux ai-safety machine-learning-security backdoor-attacks numpy-implementation data-poisoning adversarial-ml agentic-ai-security shell-command-classifier

Updated Dec 14, 2025
Python

Ashfaaq98 / ai-security-research

A collection of resources documenting my research and learning journey in AI System Security.

research resources ai-security adversarial-ml llm-security agentic-ai ai-red-teaming

Updated Nov 9, 2025

CassianLee14 / SentinEL-Adversarial-ML

Hybrid Threat Intelligence Engine with Explainable AI (XAI) and Automated Triage.

python machine-learning scikit-learn forensics secops cybersecurity threat-intelligence explainable-ai xai phishing-detection adversarial-ml

Updated Dec 30, 2025
Python

Gokkulnath / PaperReading

Placeholder for Annotated Research Papers in Deep learning discussed in Blog Posts. Most of the papers related to Adversarial ML and GAN.

deep-learning generative-adversarial-network deeplearning research-paper adversarial-machine-learning adversarial-ml

Updated Apr 12, 2021

Maze-6 / SentinEL-Adversarial-ML

Hybrid Threat Intelligence Engine with Explainable AI (XAI) and Automated Triage.

python machine-learning scikit-learn forensics secops cybersecurity threat-intelligence explainable-ai xai phishing-detection adversarial-ml

Updated Dec 30, 2025
Python

arcanjohacklindo / security-vulnerabilities-cli-llm

🔍 Analyze security vulnerabilities in CLI-based LLM deployments, drawing insights from 95 peer-reviewed sources to enhance AI tool safety.

security cybersecurity arxiv research-paper machine-learning-security ai-security adversarial-ml prompt-injection llm-security cli-security

Updated Dec 30, 2025
HTML

raghavpoonia / ai-security-mastery

Complete 90-day learning path for AI security: ML fundamentals → LLM internals → AI threats → Detection engineering. Built from first principles with NumPy implementations, Jupyter notebooks, and production-ready detection systems.

machine-learning deep-learning jupyter-notebook owasp pytorch cybersecurity security-research ai-security threat-detection mlops detection-engineering adversarial-ml ai-red-team prompt-injection llm-security

Updated Dec 30, 2025

SaharZargarzadeh / Explainable-AI-Assistant-IoT

A Gemini-powered explainable AI assistant that analyzes and interprets anomalies in IoT power signals using RAG, few-shot prompting, and embeddings. Built during the 2025 Google GenAI Capstone.

gemini iot-security explainable-ai rag adversarial-ml google-capstone llm genai power-anomaly-detection

Updated Jun 20, 2025
Jupyter Notebook

depalmar / ai_for_the_win

Complete AI-powered security training program with 25 hands-on labs, 15 CTF challenges, and enterprise integrations. Learn ML-based threat detection, LLM security analysis, adversarial ML, and cloud security. From beginner to expert.

python docker machine-learning ai incident-response dfir cybersecurity ransomware ctf siem malware-analysis red-team threat-intelligence threat-detection adversarial-ml llm langchain mcp-server

Updated Dec 30, 2025
Python

roynaldo1234 / meta-ai-bug-bounty

Meta AI Bug Bounty focuses on vulnerabilities in Instagram's Group Chat feature, revealing critical security risks. Join us in improving AI safety and explore our findings on GitHub! 🐙✨

cybersecurity penetration-testing ethical-hacking responsible-disclosure security-research mitre-attack red-teaming ai-security ai-risk adversarial-ml mitre-atlas prompt-injection meta-ai llm-vulnerabilities

Updated Dec 30, 2025

Improve this page

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