LLM06: Sensitive Information Disclosure
LLM applications have the potential to reveal sensitive information, proprietary algorithms, or other confidential details through their output. This can result in unauthorized access to sensitive data, intellectual property, privacy violations, and other security breaches. It is important for consumers of LLM applications to be aware of how to safely interact with LLMs and identify the risks associated with unintentionally inputting sensitive data that may be subsequently returned by the LLM in output elsewhere.
The consumer-LLM application interaction forms a two-way trust boundary, where we cannot inherently trust the client->LLM input or the LLM->client output. It is important to note that this vulnerability assumes that certain prerequisites are out of scope, such as threat modeling exercises, securing infrastructure, and adequate sandboxing. Adding restrictions within the system prompt around the types of data the LLM should return can provide some mitigation against sensitive information disclosure, but the unpredictable nature of LLMs means such restrictions may not always be honored and could be circumvented via prompt injection or other vectors.
Common Examples of Vulnerability
- Incomplete or improper filtering of sensitive information in the LLM responses.
- Overfitting or memorization of sensitive data in the LLM training process.
- Unintended disclosure of confidential information due to LLM misinterpretation, lack of data scrubbing methods or errors.
Example Attack Scenarios
- Unsuspecting legitimate User A is exposed to certain other user data via the LLM when interacting with the LLM application in a non-malicious manner.
- User A targets a well crafted set of prompts to bypass input filters and sanitization from the LLM to cause it to reveal sensitive information (PII) about other users of the application.
- Personal data such as PII is leaked into the model via training data due to either negligence from the user themselves, or the LLM application. This case could increase risk and probability of scenario 1 or 2 above.
How to Prevent
- Integrate adequate data sanitization and scrubbing techniques to prevent user data from entering the training model data.
- Implement robust input validation and sanitization methods to identify and filter out potential malicious inputs to prevent the model from being poisoned.
- When enriching the model with data and if fine-tuning a model: (I.e. data fed into the model before or during deployment)
- Anything that is deemed sensitive in the fine-tuning data has the potential to be revealed to a user. Therefore, apply the rule of least privilege and do not train the model on information that the highest-privileged user can access which may be displayed to a lower-privileged user.
- Access to external data sources (orchestration of data at runtime) should be limited.
- Apply strict access control methods to external data sources and a rigorous approach to maintaining a secure supply chain.
- AI data leak crisis: New tool prevents company secrets from being fed to ChatGPT: Fox Business
- Lessons learned from ChatGPT’s Samsung leak: Cybernews
- Threat Modeling Example: AI Village
- OWASP AI Security and Privacy Guide: OWASP
- Ensuring the Security of Large Language Models: Experts Exchange