MIT AI Risk Repository · Risk Category · 74.02.00

Malicious Use

Open the MIT Risk Navigator All entries from Wang2025

Description

"In terms of malicious use, LLMs could be utilized to produce content with toxicity, such as hate speech, harassment, cyberbullying, causing harm to humans [25]. In addition, malicious users may jailbreak LLMs to bypass their safety constraints for fraudulent purposes [123, 225]."

From A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy (Wang2025), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain: 4. Malicious actors
Subdomain: —
Causal entity: AI
Intent: Intentional
Timing: Post-deployment

Other entries from Wang2025

Inherent Risk Risk Category
Privacy - Membership Inference Attack (MIA) Risk Sub-Category · 2.2
Privacy - Data Extraction Attack (DEA) Risk Sub-Category · 2.2
Privacy - Prompt Inversion Attack (PIA) Risk Sub-Category · 2.2
Privacy - Attribute Inference Attack (AIA) Risk Sub-Category · 2.2
Privacy - Model Extraction Attack (MEA) Risk Sub-Category · 2.2
Hallucination Risk Sub-Category · 3.1
Hallucination Additional evidence
Value-related risks in LLMs Risk Sub-Category · 7.1
Value-related risks in LLMs Additional evidence
Toxicity in LLM Malicious Use Risk Sub-Category · 1.2
Toxicity in LLM Malicious Use Additional evidence