This page provides the attacks and factors that have a negative impact “Service disruption due to high consumption of AI resources” in the information systems aspect in the AI Security Map, the defense methods and countermeasures against them, as well as the relevant AI technologies, tasks, and data. It also indicates related elements in the external influence aspect.
Attack or cause
Defensive method or countermeasure
- Token limit
- AI access control
Targeted AI technology
- LLM
Task
- Generation
Data
- Text
Related external influence aspect
- Reputation
- Physical impact
- Psychological impact
- Financial impact
- Economy
- Critical infrastructure
- Medical care
References
Model DoS
- Sponge Examples: Energy-Latency Attacks on Neural Networks, 2021
- Sponge Examples: Energy-Latency Attacks on Neural Networks, 2021
- NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models, 2022
- Safeguard is a Double-edged Sword: Denial-of-service Attack on Large Language Models, 2024
- Denial-of-Service Poisoning Attacks against Large Language Models, 2024
- Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images, 2024