发现信息
- 作者:Erik Imgrund, Anna Wimbauer, Klim Kireev, Konrad Rieck
- 年份:2026
- 发表源:ACM Workshop on Artificial Intelligence and Security (AISec)
- OpenAlex ID:https://openalex.org/W7171563741
- DOI:https://doi.org/10.1145/3847352.3848097
- arXiv:待核验
- 检索主题:memory-learning
- OpenAlex 引用数快照:1(2026-11-12)
摘要线索
Large language models now power autonomous agents capable of complex, multi-step tasks in different environments. Accurate and reliable execution of these tasks requires the agent to predict the results of its actions. Recent research proposes to enhance predictive capabilities via specially trained environment simulators—world models. While world models can improve performance, they can also mislead agents into executing harmful actions, creating significant security and privacy risks. In this paper, we raise security concerns regarding the usage of world models in agentic systems. We discover a range of world model specific vulnerabilities, which can be exploited in terminal-based agents to execute malicious code or extract sensitive data. To facilitate future development, we introduce a security benchmark dataset designed for text-based world models. We argue that some risks are intrinsic to approximate world modeling, and show that attackers can induce mispredictions in agentic pipelines with up to 95 % success rate, possibly resulting in unintended command execution, denial of service, drainage of wallet and private information extraction. Finally, we provide practical recommendations for practitioners to mitigate the discovered harms and harden agentic systems.
核验与筛选
- 当前状态:待筛选、去重和一手来源核验。
- OpenAlex 元数据和引用数只用于发现,不作为正式引文或质量判断。
- 记录正式版本、venue、方法细节、实验协议和局限后,才迁入稳定论文卡片。