Gianfranco's Notes
  • GitHub

    Machine Learning/AI Safety

    Adversarial Machine Learning - A Taxonomy And Terminology Of Attacks And Mitigations →
    AI Agent Security →
    AI Safety →
    Automated Red Teaming With GOAT - The Generative Offensive Agent Tester →
    Can’t Hide Behind The API-Stealing Black-Box Commercial Embedding Models →
    Excessive Agency →
    Exploiting LLM APIs →
    Fine-Tuning LLMs For Cybersecurity →
    Fraudulent Scam By Unknown Remote Attacker →
    Injection Prompts →
    Insecure Output Handling →
    Insecure Plugin Design →
    Internet Of Agents - A New Era For Cybersecurity →
    Model Denial Of Service →
    Model Theft →
    Overreliance →
    Prompt Injection →
    Prompt Injection Defense Measures →
    Prompt Injection Types →
    Prompts Should Not Be Seen As Secrets →
    Red Teaming In GenAI →
    Security Of Reasoning Models →
    Sensitive Information Disclosure →
    Supply Chain Attack →
    Training Data Poisoning →
    Vulnerabilities In LLM-base Applications →