SIGNAL//DESK
AI securitysrc: OWASP LLM Top 10

Sensitive Information Disclosure

This happens when an AI accidentally spills secrets it shouldn't, like sharing someone else's private information, passwords, or company trade secrets in its answers.

A security vulnerability where an LLM inadvertently exposes sensitive data—such as PII, credentials, or proprietary information—by regurgitating training data or leaking details from its input context during inference.

An AI security failure mode characterized by the unauthorized exfiltration of confidential data, including PII, credentials, or proprietary intellectual property, resulting from the model's failure to maintain data boundaries during generation, whether through the memorization and subsequent regurgitation of training corpus artifacts or the improper inclusion of sensitive context in the output stream.

evolution

  1. 2020-05 · history
    GPT-3 Training Data Memorization

    Researchers demonstrated that large language models could inadvertently memorize and regurgitate verbatim training data, including PII.

  2. 2022-11 · history
    ChatGPT Public Launch

    The widespread adoption of consumer-facing LLMs highlighted the risk of users inadvertently inputting sensitive corporate data into public models.

  3. 2023-03 · history
    ChatGPT History Leak

    A bug in the Redis client library caused ChatGPT users to see the titles of other users' chat histories, marking a major real-world PII disclosure incident.

  4. 2023-05 · history
    Samsung Data Leak

    Samsung employees accidentally leaked proprietary source code and internal meeting notes by using ChatGPT to assist with work tasks.

  5. 2023-12 · history
    Training Data Extraction Attacks

    Researchers proved that simple prompt injection techniques could force models like ChatGPT to output large volumes of their underlying training data.


← all terms