Residual AI system security and availability weaknesses
The system is broadly vulnerable to attack or disruption, including denial-of-service and resource-exhaustion (sponge) attacks.
- Risk family
- Security & adversarial
- MIT domain
- 2. Privacy & Security
- MIT subdomain
- 2.2 > AI system security vulnerabilities and attacks
- AI type
- GPAI, Classical_ML, Agentic
- Scope
- System
- Source standard
- MIT AI Risk Repository v4
Provenance
10 entries across 8 papers
- Cui2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems02.04.00 02.10.04
- Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.27.01
- Habbal2024Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, Applications, Challenges and Future Research Directions29.03.00 29.03.02
- Saghiri2022A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions39.06.00
- Tan2022The Risks of Machine Learning Systems15.02.03
- Wang2025A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy74.01.03
- Wirtz2022Governance of artificial intelligence: A risk and guideline-based integrative framework19.01.04
- Zeng2024AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies50.01.02
Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.
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.
1- A.11 ISO/IEC 23894 Annex A A.11
2- A.4.5 ISO/IEC 42001 Annex A A.4.5
- A.6.2.4 ISO/IEC 42001 Annex A A.6.2.4
2- Art. 15
- CoP S&S Ch. Commitment 6
19Expanded into this risk’s technique sub-risks.
12- AISubtech-13.1.1 Compute Exhaustion
- AISubtech-13.1.2 Memory Flooding
- AISubtech-13.1.3 Model Denial of Service
- AISubtech-13.1.4 Application Denial of Service
- AISubtech-13.1.5 Decision Paralysis Attacks
- AISubtech-13.2.1 Service Misuse for Cost Inflation
- AISubtech-14.1.2 Insufficient Access Controls partial
- AISubtech-9.1.1 Code Execution partial
- AISubtech-9.1.2 Unauthorized or Unsolicited System Access partial
- AISubtech-9.1.3 Unauthorized or Unsolicited Network Access partial
- AISubtech-9.1.4 Injection Attacks (SQL, Command Execution, XSS) partial
- AISubtech-9.1.5 Template Injection (SSTI) partial
2- NISTAML.01 Availability Violations
- NISTAML.014 Energy-latency
1- GENAI.9 Information Security
1- LLM10:2025 Unbounded Consumption
2- ASI03 Identity and Privilege Abuse
- ASI05 Unexpected Code Execution (RCE)
Sub-risks (9)
Technique-level decompositions of this risk, each anchored to the MITRE ATLAS technique it derives from.
Stolen or abused legitimate credentials grant access to the AI system and its data.
The AI service is flooded with requests to degrade or deny availability to legitimate users.
Adversaries deliberately drive the AI service beyond normal load to inflate operating cost.
The system is spammed with inputs that inflate false detections and overwhelm downstream review.
A compromised AI system is abused to cause financial, reputational, user, or societal harm beyond the system itself.
A weakness in the internet-facing AI application is exploited to gain access.
Users are compromised by visiting attacker-influenced content during normal AI system use.
An attacker breaks out of the AI system's container or sandbox to reach the host.
AI-enabled components are exploited or manipulated to compromise the underlying machine.
More in Security & adversarial
See all Security & adversarial 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.