AIBlindspotby Velinor

Test a use caseBook AI audit

Public Database

Case Studies

Submit a case study →

Every approved AI failure case, classified against the AI Blindspot Framework. New to AIBlindspot? Start with the overview or the methodology.

HUMHUM-0064/5NewOtherGlobal

AI Model Outputs Infringe Third-Party Copyright

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — AI Risk Atlas (IBM2025)Ingested —

TECTEC-0014/5NewFinanceGlobal

Algorithmic Trading Feedback Loops and Multi-Agent System Instability

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Multi-Agent Risks from Advanced AI (Hammond2025)Ingested —

OPSOPS-0013/5NewOtherGlobal

AI Systems in Nuclear Research Pose Radiological and Security Risks

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy (Tang2025)Ingested —

TECTEC-0015/5NewOtherGlobal

Multi-Agent AI Systems Develop Unintended Capabilities Through Competitive Co-evolution

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Multi-Agent Risks from Advanced AI (Hammond2025)Ingested —

OPSOPS-0014/5NewOtherGlobal

AI Systems Developing Value Systems Divergent From Human Intent

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — The Dark Sides of Artificial Intelligence: An Integrated AI Governance Framework for Public Administration (Wirtz2020)Ingested —

SECSEC-0025/5NewDefenceGlobal

Frontier AI Enables Advanced Offensive Cyber Weapon Development

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Frontier AI Risk Management Framework (v1.0) (Tse2025)Ingested —

SECSEC-0014/5NewOtherGlobal

AI Coding Tools Lower Barrier to Polymorphic Malware Development

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Taxonomy of Risks posed by Language Models (Weidinger2022)Ingested —

GOVGOV-0014/5NewOtherGlobal

Loss of Human Control Over Artificial General Intelligence Systems

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — The risks associated with Artificial General Intelligence: A systematic review (McLean2023)Ingested —

TECTEC-0013/5NewEnergyGlobal

Multi-Agent AI Systems Can Fail Even When Each Agent Passes Safety Checks

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024)Ingested —

SECSEC-0013/5NewOtherGlobal

Safety Fine-Tuning Bypass via Encoded Text and Low-Resource Languages

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024)Ingested —

HUMHUM-0053/5NewOtherGlobal

Generative AI Depresses Pay and Job Security for Creative Professionals

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Sociotechnical Safety Evaluation of Generative AI Systems (Weidinger2023)Ingested —

TECTEC-0014/5NewOtherGlobal

Multi-Agent LLM Systems Can Develop Unpredictable Emergent Behaviours

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024)Ingested —

SECSEC-0014/5NewTechnologyGlobal

LLM Backdoor Attack Evades Post-Training Security Controls

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy (Wang2025)Ingested —

SECSEC-0014/5NewOtherGlobal

Generative AI Misuse of Intellectual Property and Personal Identity Rights

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents (Li2025)Ingested —

DATDAT-0014/5NewGovernmentGlobal

LLMs Express Extremist Views and Political Bias in Government Contexts

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements (Deng2023)Ingested —

HUMHUM-0034/5NewOtherGlobal

Chinese LLM Validates Self-Harm Method Described by User

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Safety Assessment of Chinese Large Language Models (Sun2023)Ingested —

HUMHUM-0034/5NewOtherGlobal

LLM Safety Benchmark Reveals Physical Health Advice Failures

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions (Zhang2023)Ingested —

OPSOPS-0014/5NewTransportGlobal

General-Purpose AI Miscontrol of Critical Infrastructure Networks

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Frontier AI Risk Management Framework (v1.0) (Tse2025)Ingested —

TECTEC-0014/5NewOtherGlobal

Multi-Agent AI Systems Developing Dangerous Emergent Capabilities

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Multi-Agent Risks from Advanced AI (Hammond2025)Ingested —

DATDAT-0024/5NewOtherGlobal

LLM Training Data Memorisation Leaks Personal Information

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Ethical and social risks of harm from language models (Weidinger2021)Ingested —

HUMHUM-0044/5NewOtherGlobal

Anthropomorphic AI Assistants Exploit Emotional Trust to Extract Private Data

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — The Ethics of Advanced AI Assistants (Gabriel2024)Ingested —

OPSOPS-0014/5NewOtherGlobal

Chatbot Makes Unauthorised Commitments on Behalf of Deployer

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Emerging Risks and Mitigations for Public Chatbots: LILAC v1 (Stanley2024)Ingested —

BUSBUS-0054/5NewGovernmentGlobal

AI Enabling Irreversible Concentration of Government Power

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — An Overview of Catastrophic AI Risks (Hendrycks2023)Ingested —

GOVGOV-0064/5NewOtherGlobal

Opaque AI Decision-Making Leaves Users Without Explanation or Recourse

Recent case. Full summary visible to registered users — sign in to read.

Source: MIT AI Risk Repository — Social Impacts of Artificial Intelligence and Mitigation Recommendations: An Exploratory Study (Paes2023)Ingested —

Beyond accidental failureNational Security

We also track 20 hostile uses of AI.

National Security dashboard →

The public database covers AI that fails by accident. AIBlindspot National Security — exclusive to the Defence tier — tracks AI used as a weapon, mapped by capability:

State-Sponsored AI Operations: 6
AI-Enabled Disinformation: 5
Adversarial Attacks on AI: 0
Autonomous Weapon Incidents: 1
AI-Assisted Cyber Attacks: 5
Dual-Use AI Misuse: 3