Record summary
A quick snapshot of what this page covers.
Records108Records included in this view.
SourcePublicBuilt from public source data.
ModeStaticPrepared as a ready-to-read page.
Domain summary
A group of related risks from the AI Risk database.
108 AI risk records are grouped under 2.2 > AI system security vulnerabilities and attacks in 2. Privacy & Security.
Domain2. Privacy & Security
Subdomain2.2 > AI system security vulnerabilities and attacks
Risks108
Top categoryMisuse tactics to compromise GenAI systems (Model integrity)
Top timing2 - Post-deployment
Risk records
Individual risks in this group.
A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms
1 - Intentional2 - Post-deployment
A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions
1 - Intentional3 - Other
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional2 - Post-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional2 - Post-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional2 - Post-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional2 - Post-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional2 - Post-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional1 - Pre-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional1 - Pre-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional1 - Pre-deployment
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
1 - Intentional2 - Post-deployment
A Taxonomy of Systemic Risks from General-Purpose AI
2 - Unintentional2 - Post-deployment
A Taxonomy of Systemic Risks from General-Purpose AI
1 - Intentional2 - Post-deployment
A Taxonomy of Systemic Risks from General-Purpose AI
3 - Other3 - Other
AGI Safety Literature Review
2 - Unintentional1 - Pre-deployment
AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks
1 - Intentional1 - Pre-deployment
AI Risk Atlas
1 - Intentional1 - Pre-deployment
AI Risk Atlas
1 - Intentional2 - Post-deployment
AI Risk Atlas
1 - Intentional2 - Post-deployment
AI Risk Atlas
1 - Intentional2 - Post-deployment
AI Risk Atlas
1 - Intentional3 - Other
AI Risk Atlas
1 - Intentional2 - Post-deployment
AI Risk Atlas
1 - Intentional2 - Post-deployment
AI Risk Atlas
1 - Intentional2 - Post-deployment
AI Risk Atlas
1 - Intentional2 - Post-deployment
AI Risk Atlas
2 - Unintentional2 - Post-deployment
AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosures
2 - Unintentional2 - Post-deployment
AI Safety Governance Framework
3 - Other3 - Other
AI Safety Governance Framework
1 - Intentional2 - Post-deployment
AI Safety Governance Framework
3 - Other3 - Other
AI Safety Governance Framework
3 - Other3 - Other
AI Safety Governance Framework
2 - Unintentional2 - Post-deployment
Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, Applications, Challenges and Future Research Directions
1 - Intentional2 - Post-deployment
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
3 - Other3 - Other
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
2 - Unintentional3 - Other
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
1 - Intentional2 - Post-deployment
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
1 - Intentional2 - Post-deployment
Foundational Challenges in Assuring Alignment and Safety of Large Language Models
1 - Intentional1 - Pre-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional2 - Post-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional2 - Post-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional2 - Post-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional2 - Post-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional2 - Post-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional1 - Pre-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional2 - Post-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional2 - Post-deployment
Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data
1 - Intentional2 - Post-deployment
Mapping the Ethics of Generative AI: A Comprehensive Scoping Review
1 - Intentional3 - Other
Regulating under Uncertainty: Governance Options for Generative AI
1 - Intentional2 - Post-deployment
Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems
2 - Unintentional1 - Pre-deployment
Source
Where this page information comes from.
Original source
Original source links
Open the public records and source datasets used for this page.