BackPrivacy Violation

Privacy Violation

Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment

Liu et al. (2024)

Sub-category

Risk Domain

2.1Compromise of privacy by leaking or correctly inferring sensitive information

AI systems that memorize and leak sensitive personal data or infer private information about individuals without their consent. Unexpected or unauthorized sharing of data and information can compromise user expectation of privacy, assist identity theft, or cause loss of confidential intellectual property.

machine learning models are known to be vulnerable to data privacy attacks, i.e. special techniques of extracting private information from the model or the system used by attackers or malicious users, usually by querying the models in a specially designed way(p. 15)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Supporting Evidence (1)

Privacy attacks on LLMs, leveraged by the memorization power of LLMs, raise similar concerns on the possibility of leaking personal information from the outputs [53, 187]. Recent works [188, 189, 190, 191, 192] have shown that an attacker can extract personal or sensitive information or private training samples from LLM’s training data by querying LLMs alone.(p. 16)

Part of Safety