Record summary
A quick snapshot of what this page covers.
Techniques3Attack methods connected to this risk.
Mitigations4Defenses that may help with related attacks.
Domain4. Malicious Actors & MisuseThe broad risk area this belongs to.
Risk profile
How this risk is described and categorized.
"LM prediction can potentially be used to increase the effectiveness of crimes such as email scams, which can cause financial and psychological harm. While LMs may not reduce the cost of sending a scam email - the cost of sending mass emails is already low - they may make such scams more effective by generating more personalised and compelling text at scale, or by maintaining a conversation with a victim over multiple rounds of exchange."
Domain4. Malicious Actors & Misuse
Subdomain4.3 > Fraud, scams, and targeted manipulation
Entity1 - Human
Intent1 - Intentional
Timing2 - Post-deployment
CategoryMalicious Uses
SubcategoryFacilitating fraud, scames and more targeted manipulation
Suggested mitigations
Defenses that may help with related attacks.
User Training
Business and Data UnderstandingData Preparation+4 more
Deepfake Detection
DeploymentMonitoring and Maintenance+2 more
Restrict Number of AI Model Queries
Business and Data UnderstandingDeployment+1 more
Control Access to AI Models and Data in Production
DeploymentMonitoring and Maintenance
Source
Research source for this risk, when available.
Included resource
Ethical and social risks of harm from language models
Original source
MIT AI Risk Repository
Open the public repository used for AI risk records and taxonomy fields.