Machine_Learning_CTF_Challenges
Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation.
- 279
- Python
- 6 mo ago
alexdevassy
Project Lead@OWASP SAPKiln | Penetration Testing | Vulnerability Management | SAP & AI/ML Security
Built from alexdevassy's public GitHub profile. Not on Take My Repo yet, so there are no posts or updates here.
Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation.
Vulnerability impact analyzer that reduces false positives in SCA tools by performing intelligent code analysis. Uses agentic AI with open source models to understand CVEs and verify actual vulnerability impact in your codebase. Keeps your code secure with on-premises execution and human-in-the-loop verification.
This research introduces MCP Signature Cloaking - a novel backdoor technique that allows attackers to exploit hidden parameters in MCP servers, concealing malicious behavior behind interfaces that appear legitimate to both developers and AI models.
Node js Script which scans for open ports in network, establish connection with blockchain node and attempts to brute force user accounts
connecting raspberry pi 2 with ethereum blockchain
Practical Implementations of Explainable AI (XAI) techniques for Responsible AI
Sample money transfer application in hyperledger composer