Autonomy Comes with Costs: Detecting Denial-of-Service Vulnerabilities Caused by Resource Abusing in LLM-based Agents
Abstract
The artifact package comprises: The set of 20 agent applications employed in our experiments. The baseline implementations prepared for comparative evaluation. For ethical considerations, the prototype of **AgentDoS** is only conditionally available at https://zenodo.org/records/18091114 Access is restricted to qualified researchers who complete a formal request and pass the review process.
Fields of Study & Subjects
Adversarial Robustness in Machine Learning
Network Security and Intrusion Detection
Security and Verification in Computing
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 1 January 2026