This page provides the attacks and factors that have a negative impact “Unauthorized access due to privilege abuse” 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
- Indirect prompt injection
- Memory poisoning
- Identity spoofing
- Integrity violation
Defensive method or countermeasure
- Permission management
- Defensive methods to prevent compromise of causal elements
Targeted AI technology
- AI agent
Task
- Perception
- Decision-making
- Action
Data
- Text
Related external influence aspect
References
Indirect prompt injection
- Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection, 2023
- Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models, 2023
- Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs, 2023
- Defending Against Indirect Prompt Injection Attacks With Spotlighting, 2024
- InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents, 2024