Probing LLM generated code for open source supply chain attacks | San Francisco .
Cities (243) ▾

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

Sign in View FAQ
June 25, 2026 · San Francisco

Securing LLM-Generated Code

Explore LLM-generated code for supply chain attack vulnerabilities. Learn how to evaluate and measure these risks yourself in this mainstage presentation.

Python Garak LLM LLM vulnerability scanner
Overview

Evals and code for detecting supply chain attacks in LLM generated code

Links
Tech stack
  • Python
    Python: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.
    Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
  • Garak
    An open-source vulnerability scanner that probes large language models for security weaknesses, jailbreaks, and data leaks.
    Garak (Generative AI Red-teaming & Assessment Kit) is an open-source command-line tool supported by NVIDIA that acts as an vulnerability scanner for LLMs. It functions like a network security scanner (think Nmap, but built specifically for AI) by systematically probing models, dialogue systems, and guardrails for failure modes. Garak uses a structured framework of probes, generators, and detectors to test for prompt injection, hallucinations, toxic outputs, and data leakage. It supports major platforms (including OpenAI, Hugging Face, and custom REST endpoints) and outputs detailed JSONL reports to help developers patch security gaps before deployment.
  • LLM
    Large Language Models (LLMs) are deep learning models, built on the Transformer architecture, that process and generate human-quality text and code at scale.
    LLMs are a class of foundation models: massive, pre-trained neural networks (often with billions to trillions of parameters) that leverage the self-attention mechanism of the Transformer architecture (introduced in 2017) to predict the next token in a sequence. Trained on vast datasets (e.g., Common Crawl's 50 billion+ web pages), these models—like GPT-4, Gemini, and Claude—acquire predictive power over syntax and semantics. They function as general-purpose sequence models, enabling critical applications such as complex content generation, language translation, and automated code completion (e.g., GitHub Copilot). Their core value: generalizing across diverse tasks with minimal task-specific fine-tuning.
  • LLM vulnerability scanner
    An open-source vulnerability scanner that probes large language models for security flaws, jailbreaks, and data leaks.
    Think of garak as the Nmap for generative AI. This command-line security tool probes LLMs and AI applications for critical weaknesses (including prompt injection, hallucination, data leakage, and toxic output generation). Backed by NVIDIA and a highly active open-source community, garak automates the red-teaming process by running targeted attack simulations against your model endpoints. It provides structured, actionable reports so security teams can identify and patch vulnerabilities before deployment.
Events Gallery FAQ Sponsor