MIT AI Risk Repository · domain 2: Privacy & Security

2.2 AI system security vulnerabilities and attacks

Vulnerabilities in AI systems, software development toolchains, and hardware that can be exploited, resulting in unauthorized access, data and privacy breaches, or system manipulation causing unsafe outputs or behavior.

Risk entries
112
Frameworks citing it
12
Recorded incidents
24
Incidents since 2020
20
Causal entity (risk entries)
Causal entity (risk entries) 87 0 Human: 87 Human 87 Other: 18 Other 18 AI: 6 AI 6 Not coded: 1 Not coded 1
Causal entity (risk entries)
LabelValue
Human87
Other18
AI6
Not coded1
Intent (risk entries)
Intent (risk entries) 83 0 Intentional: 83 Intentional 83 Unintentional: 16 Unintentional 16 Other: 12 Other 12 Not coded: 1 Not coded 1
Intent (risk entries)
LabelValue
Intentional83
Unintentional16
Other12
Not coded1
Timing (risk entries)
Timing (risk entries) 64 0 Post-deployment: 64 Post-deployment 64 Pre-deployment: 25 Pre-deployment 25 Other: 22 Other 22 Not coded: 1 Not coded 1
Timing (risk entries)
LabelValue
Post-deployment64
Pre-deployment25
Other22
Not coded1
Recorded incidents per yearIncident date; current year partial
Recorded incidents per year 7 0 2017: 3 2017 3 2019: 1 2019 1 2022: 2 2022 2 2023: 3 2023 3 2024: 3 2024 3 2025: 5 2025 5 2026: 7 2026 7
Recorded incidents per year
LabelValue
20173
20191
20222
20233
20243
20255
20267
Entries by levelRisk categories, subcategories and additional evidence coded to this subdomain
Entries by level 96 0 Risk Category: 16 Risk Category 16 Risk Sub-Category: 96 Risk Sub-Category 96
Entries by level
LabelValue
Risk Category16
Risk Sub-Category96
  • Poisoning

    "Data Poisoning involves deliberately corrupting a model’s training dataset to introduce vulnerabilities, derail its learning process, or cause it to make incorrect predictions (Carlini et al., 2023)....

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

  • Misuse tactics to compromise GenAI systems (Data integrity)

    -

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

  • Privacy compromise

    "Privacy Compromise attacks reveal sensitive or private information that was used to train a model. For example, personally identifiable information or medical records."

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

  • Data exfiltration

    "Data Exfiltration goes beyond revealing private information, and involves illicitly obtaining the training data used to build a model that may be sensitive or proprietary. Model Extraction is the sam...

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

  • Security

    every piece of software, including learning systems, may be hacked by malicious users

    A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions (Saghiri2022) · Human · Intentional · Other

  • Data poisoning

    "Data poisoning describes an attack in the form of an injection of malicious data into the training set. If not prevented, this attack leads the AI system to learn unintended behavior."

    AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks (Schnitzer2024) · Human · Intentional · Pre-deployment

  • Security

    "Encompasses vulnerabilities in AI systems that compromise their integrity, availability, or confidentiality. Security breaches could result in significant harm, ranging from flawed decision-making to...

    AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosures (Sherman2023) · AI · Unintentional · Post-deployment

  • Security

    "Artificial intelligence comes with an intrinsic set of challenges that need to be considered when discussing trustworthiness, especially in the context of functional safety. AI models, especially tho...

    Sources of Risk of AI Systems (Steimers2022) · Other · Other · Post-deployment

  • Instruction Attacks

    "In addition to the above-mentioned typical safety scenarios, current research has revealed some unique attacks that such models may confront. For example, Perez and Ribeiro (2022) found that goal hij...

    Safety Assessment of Chinese Large Language Models (Sun2023) · Human · Intentional · Post-deployment

  • Goal Hijacking

    "It refers to the appending of deceptive or misleading instructions to the input of models in an attempt to induce the system into ignoring the original user prompt and producing an unsafe response."

    Safety Assessment of Chinese Large Language Models (Sun2023) · Human · Intentional · Post-deployment

  • Role Play Instruction

    "Attackers might specify a model’s role attribute within the input prompt and then give specific instructions, causing the model to finish instructions in the speaking style of the assigned role, whic...

    Safety Assessment of Chinese Large Language Models (Sun2023) · Human · Intentional · Post-deployment

  • Unsafe Instruction Topic

    "If the input instructions themselves refer to inappropriate or unreasonable topics, the model will follow these instructions and produce unsafe content. For instance, if a language model is requested...

    Safety Assessment of Chinese Large Language Models (Sun2023) · Human · Intentional · Post-deployment

  • Inquiry with Unsafe Opinion

    "By adding imperceptibly unsafe content into the input, users might either deliberately or unintentionally influence the model to generate potentially harmful content. In the following cases involving...

    Safety Assessment of Chinese Large Language Models (Sun2023) · Human · Intentional · Post-deployment

  • Reverse Exposure

    "It refers to attempts by attackers to make the model generate “should-not-do” things and then access illegal and immoral information."

    Safety Assessment of Chinese Large Language Models (Sun2023) · Human · Intentional · Post-deployment

  • Security

    This is the risk of loss or harm from intentional subversion or forced failure.

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

  • Risks from models and algorithms (Risks of stealing and tampering)

    "Core algorithm information, including parameters, structures, and functions, faces risks of inversion attacks, stealing, modification, and even backdoor injection, which can lead to infringement of i...

    AI Safety Governance Framework (TC2602024) · Other · Other · Other

  • Risks from models and algorithms (Risks of adversarial attack)

    "Attackers can craft well-designed adversarial examples to subtly mislead, influence, and even manipulate AI models, causing incorrect outputs and potentially leading to operational failures."

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

  • Risks from AI systems (Risks of exploitation through defects and backdoors)

    "The standardized API, feature libraries, toolkits used in the design, training, and verification stages of AI algorithms and models, development interfaces, and execution platforms may contain logica...

    AI Safety Governance Framework (TC2602024) · Human · Other · Other

  • Risks from AI systems (Risks of computing infrastructure security)

    "The computing infrastructure underpinning AI training and operations, which relies on diverse and ubiquitous computing nodes and various types of computing resources, faces risks such as malicious co...

    AI Safety Governance Framework (TC2602024) · Human · Other · Other

  • Cyberspace risks (Risks of security flaw transmission caused by model reuse)

    "Re-engineering or fine-tuning based on foundation models is commonly used in AI applications. If security flaws occur in foundation models, it will lead to risk transmission to downstream models."

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

  • Centralized platforms deployed at scale

    "The widespread use of common AI platforms can create centralized points of failure, making systems more vulnerable to disruptions or attacks"

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

  • Limitations in adversarial robustness

    "AI models and systems are vulnerable to manipulation through adversarial inputs."

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

  • Risks from network interconnectivity

    "The interconnectedness of AI networks can create vulnerabilities, where issues in one part of the network can have cascading effects across the system."

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

  • Privacy - Membership Inference Attack (MIA)

    "inferring whether a given text record is used for training LLM"

    A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy (Wang2025) · Human · Intentional · Post-deployment

  • Privacy - Data Extraction Attack (DEA)

    "extracting the text records that exist in the training dataset"

    A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy (Wang2025) · Human · Intentional · Post-deployment