MR-028 Model & system behaviour Both scope

AI-enabled fraud, scams and social engineering

The system is used to conduct or scale fraud, scams, phishing, social engineering, or market manipulation.

Risk family: Model & system behaviour
MIT domain: 4. Malicious Actors & Misuse
MIT subdomain: 4.3 > Fraud, scams, and targeted manipulation
AI type: GPAI, Agentic
Scope: Both
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

MIT source entries

44 entries across 24 papers

Anwar2024Foundational Challenges in Assuring Alignment and Safety of Large Language Models73.03.02 73.07.02
Bengio2024International Scientific Report on the Safety of Advanced AI49.01.01 49.01.02
DSIT2023Capabilities and Risks from Frontier AI67.03.02
EPIC2023Generating Harms - Generative AI's impact and paths forwards31.01.01 31.04.00
Ferrara2023GenAI against humanity: nefarious applications of generative artificial intelligence and large language models46.02.00 46.02.01 46.02.03
Gabriel2024The Ethics of Advanced AI Assistants24.03.01 24.03.02 24.03.14 24.11.02
Ghosh2024AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons57.02.04
Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.09.03 62.31.09 62.32.03
Hammond2025Multi-Agent Risks from Advanced AI63.02.03 63.08.02 63.10.03
Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.07.01
Maham2023Governing General Purpose AI: A Comprehensive Map of Unreliability, Misuse and Systemic Risks52.02.01
NIST2024Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile48.09.00
Shevlane2023Model Evaluation for Extreme Risks25.09.00
Sun2023Safety Assessment of Chinese Large Language Models27.01.03
TC2602024AI Safety Governance Framework45.02.04
Tse2025Frontier AI Risk Management Framework (v1.0)72.01.01 72.05.10 72.06.05
Vidgen2024Introducing v0.5 of the AI Safety Benchmark from MLCommons23.02.05
Wang2025A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy74.02.00
Weidinger2021Ethical and social risks of harm from language models17.04.02
Weidinger2022Taxonomy of Risks posed by Language Models16.04.00 16.04.03
Weidinger2023Sociotechnical Safety Evaluation of Generative AI Systems18.04.00
Yampolskiy2016Taxonomy of Pathways to Dangerous Artificial Intelligence40.02.00
Zeng2024AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies50.02.07 50.03.08 50.03.09 50.04.01 50.04.06 50.04.07
Zhang2023SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions28.05.00

Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.

ISO/IEC references

23894 obj A.11; src 7 | 42001 ctrl A.9.4

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.

Sourcesframeworks that contributed to the register

A.11 ISO/IEC 23894 Annex A A.11

A.9.4 ISO/IEC 42001 Annex A A.9.4

Expanded into this risk’s technique sub-risks.

Cross-checksframeworks mapped in to test coverage

AISubtech-15.1.12 Safety Harms and Toxicity: Scams and Deception
AISubtech-15.1.7 Safety Harms and Toxicity: Financial Harm partial
AISubtech-18.1.1 Spam / Scam / Social Engineering Generation

Sub-risks (2)

Technique-level decompositions of this risk, each anchored to the MITRE ATLAS technique it derives from.

MR-028.1

User-execution social engineering

Users are manipulated into actions (opening content, running code) that compromise the AI system.

MITRE ATLAS technique: AML.T0011 User Execution

MR-028.2

AI-enabled phishing for system access

AI-generated phishing messages are used to gain access to the deployer's systems.

MITRE ATLAS technique: AML.T0052 Phishing

More in Model & system behaviour

MR-001 MR-002 MR-003 MR-004 MR-005 MR-006 MR-007 MR-008 MR-019 MR-021 MR-022 MR-023 MR-025 MR-026 MR-027 MR-029 MR-031 MR-049 MR-050 MR-051 MR-052 MR-053 MR-055 MR-056 MR-057 MR-058 MR-059 MR-061

See all Model & system behaviour risks →

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.