AI-enabled cyberattacks and offensive cyber operations
The system is used to create malware, discover/exploit vulnerabilities, or automate and scale cyberattacks (and the deployer may be a target).
- Risk family
- Model & system behaviour
- MIT domain
- 4. Malicious Actors & Misuse
- MIT subdomain
- 4.2 > Cyberattacks, weapon development or use, and mass harm
- AI type
- GPAI, Agentic
- Scope
- Both
- Source standard
- MIT AI Risk Repository v4
Provenance
32 entries across 24 papers
- Abercrombie2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms58.05.01 58.06.11
- Allianz2018The Rise of Artificial Intelligence - Future Outlooks and Emerging Risks41.05.00
- Bengio2025International AI Safety Report 202560.01.03
- Chin2025Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks68.02.00
- Cui2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems02.03.03
- EPIC2023Generating Harms - Generative AI's impact and paths forwards31.01.04
- G'sell2024Regulating under Uncertainty: Governance Options for Generative AI47.02.02
- Gabriel2024The Ethics of Advanced AI Assistants24.03.03 24.03.04 24.03.05
- Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.32.00 62.32.01 62.32.04
- Hogenhout2021A framework for ethical Ai at the United Nations06.11.00
- InfoComm2023Cataloguing LLM Evaluations43.02.01
- Ji2023AI Alignment: A Comprehensive Survey34.03.03
- Leech2024Ten Hard Problems in Artificial Intelligence We Must Get Right54.01.05
- Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.09.02
- Liu2024Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment30.04.02
- Maas2023Advancing AI Governance: A Literature Review of Problems, Options, and Proposals53.02.02
- Meek2016Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review09.05.03
- Shevlane2023Model Evaluation for Extreme Risks25.01.00
- Teixeira2022An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance42.12.00
- Tse2025Frontier AI Risk Management Framework (v1.0)72.04.02 72.06.01
- Weidinger2022Taxonomy of Risks posed by Language Models16.04.02
- Wirtz2022Governance of artificial intelligence: A risk and guideline-based integrative framework19.02.04 19.04.03
- Yampolskiy2016Taxonomy of Pathways to Dangerous Artificial Intelligence40.01.00
- Zeng2024AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies50.01.03 50.04.08
Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.
Framework crosswalk
Every framework item mapped to this risk. Items marked partial overlap only in part; definitions appear on hover where the source licence permits.
1- A.11 ISO/IEC 23894 Annex A A.11
1- A.9.4 ISO/IEC 42001 Annex A A.9.4
1Expanded into this risk’s technique sub-risks.
2- AISubtech-15.1.1 Cybersecurity and Hacking: Malware / Exploits
- AISubtech-15.1.2 Cybersecurity and Hacking: Cyber Abuse
1- GENAI.9 Information Security
Sub-risks (1)
Technique-level decompositions of this risk, each anchored to the MITRE ATLAS technique it derives from.
The model is driven to dynamically generate malicious commands or code used to attack systems.
More in Model & system behaviour
Part of the Deployer AI Risk Register, an open-source resource powered by MindXO. Version 1.0, 3 July 2026. Derived from the MIT AI Risk Repository (V4, December 2025) under CC BY 4.0; an independent derivative work, not endorsed by or affiliated with MIT. Sub-risk decomposition references MITRE ATLAS™ v5.6.0 (© 2021-2026 The MITRE Corporation, reproduced and distributed with permission). ISO/IEC and EU AI Act references are by number only. License: CC BY 4.0. Full attribution and licensing.