AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways
It addresses security challenges for AI agent developers and users, but is incremental as it reviews existing threats rather than proposing new solutions.
This survey tackles the problem of emerging security threats in AI agents, categorizing them into four key knowledge gaps and highlighting both progress and limitations in safeguarding these systems.
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and executing actions, have seen remarkable advancements in algorithm development and task performance. However, the security challenges they pose remain under-explored and unresolved. This survey delves into the emerging security threats faced by AI agents, categorizing them into four critical knowledge gaps: unpredictability of multi-step user inputs, complexity in internal executions, variability of operational environments, and interactions with untrusted external entities. By systematically reviewing these threats, this paper highlights both the progress made and the existing limitations in safeguarding AI agents. The insights provided aim to inspire further research into addressing the security threats associated with AI agents, thereby fostering the development of more robust and secure AI agent applications.