Skip to content
View fred-ai-security's full-sized avatar

Block or report fred-ai-security

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fred-ai-security/README.md

πŸ‘‹ Hi, I'm Frederick Baffour AI Security Assurance Engineer | LLM Red Teaming | Model Supply-Chain Security

I specialize in AI Security Assurance, evaluating how AI systems are tested, secured, and governed before deployment in real environments. My work covers the full lifecycle β€” from model intake and supply-chain verification through adversarial testing, RAG pipeline security, and agentic AI security assessment.

My background in enterprise security engineering informs a disciplined approach to AI systems: reproducible testing, structured methodology, and evidence-based conclusions.

πŸ” What I Work On

  • AI Security Assurance engineering across the full model lifecycle
  • LLM red teaming (Garak, PyRIT, Promptfoo β€” automated and manual)
  • Jailbreak, prompt injection, and refusal-bypass evaluation
  • RAG pipeline security β€” retrieval poisoning, context manipulation, jailbreak-through-retrieval
  • Agentic AI security β€” tool call injection, goal hijacking, privilege escalation, indirect injection
  • Model supply-chain integrity (hashing, SBOMs, provenance validation, static analysis)
  • Findings mapped to NIST AI RMF, MITRE ATLAS, and OWASP LLM Top 10 (2025)

🧰 Core Tools

  • Adversarial testing: Garak, PyRIT, Promptfoo
  • Supply-chain & CVE scanning: Syft, Grype
  • Static analysis: YARA, ClamAV, Sigcheck
  • RAG & inference: LangChain, ChromaDB, Ollama, HuggingFace CLI
  • Agentic tooling: FastMCP

πŸ“˜ Featured Work

πŸ” AI Security Assurance Labs End-to-end portfolio demonstrating a six-stage AI Security Assurance lifecycle:

  • Model intake & supply-chain verification (hashing, SBOM, provenance)
  • LLM red teaming & behavioral evaluation (1,280 Garak probes, PyRIT, Promptfoo)
  • RAG pipeline security assessment (18-test adversarial harness, LLM judge architecture)
  • Agentic AI security assessment (8 attack classes, 10-scenario harness)
  • Risk-tiered deployment recommendations with framework-mapped findings

πŸ‘‰ https://github.com/fred-ai-security/ai-security-assurance-labs

🀝 Open to Roles

  • AI Security Engineer
  • LLM Red Team Engineer
  • Model Evaluation & Assurance
  • AI Systems Security
  • AI Security Consulting & Subcontracting

πŸ“¬ Contact

Email: fbaffour@gmail.com

LinkedIn: https://www.linkedin.com/in/frederick-baffour

Popular repositories Loading

  1. ai-security-assurance-labs ai-security-assurance-labs Public

    Professional AI Security Assurance portfolio demonstrating model supply-chain security, LLM red teaming, static analysis, SBOM validation, risk classification, and governance-aligned AI safety work…

    Python

  2. fred-ai-security fred-ai-security Public