MIT AI Risk Repository · Risk Category · 73.03.00

Dual-Use Capabilities Enable Malicious Use and Misuse of LLMs

Open the MIT Risk Navigator All entries from Anwar2024

Description

"Like all technologies, LLMs have the possibility for misuse by malicious actors. Malicious use of dual- use capabilities of AI is a recurring concern within literature (Brundage et al., 2018; Hendrycks et al., 2023; Mozes et al., 2023)"

From Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain: 4. Malicious actors
Subdomain: 4.0
Causal entity: Human
Intent: Intentional
Timing: Post-deployment

How other frameworks describe this risk

Malicious Use Risks
International Scientific Report on the Safety of Advanced AI (Bengio2024)
Risks from malicious use
International AI Safety Report 2025 (Bengio2025)
Enabling malicious actors and harmful actions
Navigating the Landscape of AI Ethics and Responsibility (Cunha2023)
Malicious Use and Unleashing AI Agents
Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements (Deng2023)
Misuse risks
Capabilities and Risks from Frontier AI (DSIT2023)
Malicious Uses
The Ethics of Advanced AI Assistants (Gabriel2024)
Fine-tuning related (Ease of reconfiguring GPAI models)
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)
Democratizing access to dual-use technologies
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024)

Other entries from Anwar2024

Agentic LLMs Pose Novel Risks Risk Category · 7.2
Natural Language Underspecifies Goals Risk Sub-Category · 7.1
Goal-Directedness Incentivizes Undesirable Behaviors Risk Sub-Category · 7.2
Safety Risks from Affordances Provided to LLM-agents Risk Sub-Category · 7.2
Multi-Agent Safety Is Not Assured by Single-Agent Safety Risk Category · 7.6
Foundationality May Cause Correlated Failures Risk Sub-Category · 7.6
Groups of LLM-Agents May Show Emergent Functionality Risk Sub-Category · 7.6
Collusion between LLM-Agents Risk Sub-Category · 7.6
Misinformation and Manipulation Risk Sub-Category · 4.3
Cybersecurity Risk Sub-Category · 4.3
Cybersecurity Additional evidence
Cybersecurity Additional evidence