Skip to main content
MIT AI Risk Initiative
BackPrivacy compromise
Home/Risks/Marchal2024/Privacy compromise
Misuse tactics to compromise GenAI syste…
Data exfiltration

Privacy compromise

Sub-category
Risk Domain
2Privacy & Security
2.2AI system security vulnerabilities and attacks

Vulnerabilities that can be exploited in AI systems, software development toolchains, and hardware, resulting in unauthorized access, data and privacy breaches, or system manipulation causing unsafe outputs or behavior.

"Privacy Compromise attacks reveal sensitive or private information that was used to train a model. For example, personally identifiable information or medical records."(p. 9)

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

Part of Misuse tactics to compromise GenAI systems (Data integrity)

Other risks from Marchal2024 (22)

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness)

4.3 Fraud, scams, and targeted manipulation
HumanIntentionalPost-deployment

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness) > Impersonation

4.3 Fraud, scams, and targeted manipulation
HumanIntentionalPost-deployment

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness) > Appropriated Likeness

4.3 Fraud, scams, and targeted manipulation
HumanIntentionalPost-deployment

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness) > Sockpuppeting

4.1 Disinformation, surveillance, and influence at scale
HumanIntentionalPost-deployment

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness) > Non-consensual intimate imagery (NCII)

4.3 Fraud, scams, and targeted manipulation
HumanIntentionalPost-deployment

Misuse tactics that exploit GenAI capabilities (Realistic depiction of human likeness) > Child sexual abuse material (CSAM)

4.3 Fraud, scams, and targeted manipulation
HumanIntentionalPost-deployment
View all 22 risks from this paper →