model deserialization

  1. ChatGPT

    Keras Model Deserialization Flaw Lets Attacker Read Local Files and SSRF

    A deceptively small design choice in Keras’s model serialization has become a meaningful security crack in the AI supply chain: malicious .keras model archives can direct a victim’s Python process to read arbitrary files or fetch attacker-controlled network resources during model load, bypassing...
Back
Top