MIT AI Risk Repository · domain 4: Malicious actors

4.1 Disinformation, surveillance, and influence at scale

Using AI systems to conduct large-scale disinformation campaigns, malicious surveillance, or targeted and sophisticated automated censorship and propaganda, with the aim to manipulate political processes, public opinion and behavior.

Risk entries
84
Frameworks citing it
12
Recorded incidents
138
Incidents since 2020
132
Causal entity (risk entries)
Causal entity (risk entries) 59 0 Human: 59 Human 59 Other: 14 Other 14 AI: 9 AI 9 Not coded: 2 Not coded 2
Causal entity (risk entries)
LabelValue
Human59
Other14
AI9
Not coded2
Intent (risk entries)
Intent (risk entries) 73 0 Intentional: 73 Intentional 73 Other: 9 Other 9 Not coded: 2 Not coded 2
Intent (risk entries)
LabelValue
Intentional73
Other9
Not coded2
Timing (risk entries)
Timing (risk entries) 74 0 Post-deployment: 74 Post-deployment 74 Other: 8 Other 8 Not coded: 2 Not coded 2
Timing (risk entries)
LabelValue
Post-deployment74
Other8
Not coded2
Recorded incidents per yearIncident date; current year partial
Recorded incidents per year 50 0 2015: 2 2015 2 2016: 1 2016 1 2017: 1 2017 1 2019: 2 2019 2 2020: 6 2020 6 2021: 3 2021 3 2022: 6 2022 6 2023: 21 2023 21 2024: 50 2024 50 2025: 38 2025 38 2026: 8 2026 8
Recorded incidents per year
LabelValue
20152
20161
20171
20192
20206
20213
20226
202321
202450
202538
20268
Entries by levelRisk categories, subcategories and additional evidence coded to this subdomain
Entries by level 74 0 Risk Category: 10 Risk Category 10 Risk Sub-Category: 74 Risk Sub-Category 74
Entries by level
LabelValue
Risk Category10
Risk Sub-Category74
  • Propaganda

    LLMs can be leveraged, by malicious users, to proactively generate propaganda information that can facilitate the spreading of a target

    Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment (Liu2024) · Human · Intentional · Post-deployment

  • Politically motivated misuse

    "General purpose AI models could exacerbate existing tactics for political destabilisation, such as disinformation campaigns, and surveillance efforts if misused for political motivations. The technol...

    Governing General Purpose AI: A Comprehensive Map of Unreliability, Misuse and Systemic Risks (Maham2023 ) · Human · Intentional · Post-deployment

  • Sockpuppeting

    "Create synthetic online personas or accounts"

    Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024) · Human · Intentional · Post-deployment

  • Falisification

    "Fabricate or falsely represent evidence, incl. reports, IDs, documents"

    Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024) · Human · Intentional · Post-deployment

  • Information Integrity

    "Lowered barrier to entry to generate and support the exchange and consumption of content which may not distinguish fact from opinion or fiction or acknowledge uncertainties, or could be leveraged for...

    Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile (NIST2024) · Human · Other · Post-deployment

  • Civic and political harms

    Political harms emerge when “people are disenfranchised and deprived of appropriate political power and influence” [186, p. 162]. These harms focus on the domain of government, and focus on how algori...

    Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction (Shelby2023) · Other · Intentional · Post-deployment

  • Other ethical risks

    "Although we have discussed a number of common risks posed by ML systems, we acknowledge that there are many other ethical risks such as the potential for psychological manipulation, dehumanization, a...

    The Risks of Machine Learning Systems (Tan2022) · Human · Intentional · Post-deployment

  • Cognitive risks (Risks of usage in launching cognitive warfare)

    "AI can be used to make and spread fake news, images, audio, and videos; propagate content of terrorism, extremism, and organized crimes; interfere in the internal affairs of other countries, social s...

    AI Safety Governance Framework (TC2602024) · Human · Intentional · Post-deployment

  • Manipulation

    "The predictability of behaviour protocol in AI, particularly in some applications, can act an incentive to manipulate these systems."

    An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance (Teixeira2022) · AI · Intentional · Post-deployment

  • Large-Scale Persuasion and Harmful Manipulation Risks

    "AI systems can be gravely misused to distort public perception and compromise social stability through the generation of synthetic content (e.g., deepfakes, sophisticated fake news) and the strategic...

    Frontier AI Risk Management Framework (v1.0) (Tse2025) · Human · Intentional · Post-deployment

  • Information

    "Large-scale influence on communication and information systems, and epistemic processes more generally."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · Other · Other · Other

  • Ability to persuade

    "AI could be used to develop sophisticated tools to manipulate and persuade individuals."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · Human · Intentional · Post-deployment

  • Advertising-driven models

    "AI models and systems underpin the advertising approaches that drive much of the internet, potentially influencing societal behavior."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · AI · Intentional · Post-deployment

  • AI in totalitarian regimes

    "AI-based surveillance and manipulation could be used to maintain global totalitarian regimes."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · Human · Intentional · Post-deployment

  • Limitations in model generative accuracy

    "AI-generated deepfakes can create convincingly realistic but entirely fabricated information."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · AI · Other · Other

  • Surveillance capabilities

    "AI models and systems may grant governments or corporations increased monitoring over individuals."

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · AI · Intentional · Post-deployment

  • Widespread use of persuasion tools

    "Widespread use of AI-powered persuasion tools could lead to systemic harm"

    A Taxonomy of Systemic Risks from General-Purpose AI (Uuk2025) · Human · Other · Post-deployment

  • Elections

    "This category addresses responses that contain factually incorrect information about electoral systems and processes, including in the time, place, or manner of voting in civic elections."

    Introducing v0.5 of the AI Safety Benchmark from MLCommons (Vidgen2024) · AI · Other · Post-deployment

  • Making disinformation cheaper and more effective

    "LMs can be used to create synthetic media and ‘fake news’, and may reduce the cost of producing disinformation at scale (Buchanan et al., 2021). While some predict that it will be cheaper to hire hum...

    Ethical and social risks of harm from language models (Weidinger2021) · Human · Intentional · Post-deployment

  • Illegitimate surveillance and censorship

    "The collection of large amounts of information about people for the purpose of mass surveillance has raised ethical and social concerns, including risk of censorship and of undermining public discour...

    Ethical and social risks of harm from language models (Weidinger2021) · Human · Intentional · Post-deployment

  • Making disinformation cheaper and more effective

    "While some predict that it will remain cheaper to hire humans to generate disinformation [180], it is equally possible that LM- assisted content generation may offer a lower-cost way of creating disi...

    Taxonomy of Risks posed by Language Models (Weidinger2022) · Human · Intentional · Post-deployment

  • Illegitimate surveillance and censorship

    Anticipated risk: "Mass surveillance previously required millions of human analysts [83], but is increasingly being automated using machine learning tools [7, 168]. The collection and analysis of larg...

    Taxonomy of Risks posed by Language Models (Weidinger2022) · Human · Intentional · Post-deployment

  • Influence operations

    "Facilitating large-scale disinformation campaigns and targeted manipulation of public opinion"

    Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023) · Human · Intentional · Post-deployment

  • Defamation

    "Facilitating slander, defamation, or false accusations"

    Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023) · Human · Intentional · Post-deployment

  • Privacy and safety

    "Privacy and safety deals with the challenge of protecting the human right for privacy and the necessary steps to secure individual data from unauthorized external access. Many organizations employ AI...

    The Dark Sides of Artificial Intelligence: An Integrated AI Governance Framework for Public Administration (Wirtz2020) · Human · Intentional · Other