paperDecember 2025UnreviewedOpen access

ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications

Eranga Bandara, Amin Hass, Ross Gore, Sachin Shetty, R. Mukkamala, S. Bouk, Xueping Liang, Ng Wee Keong, K. D. Zoysa, A. Withanage, Nilaan Loganathan

International Conference on Wireless Communications and Mobile Computing

View resource

Abstract

AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task execution, and multimodal interactions through large language models (LLMs). However, these systems introduce novel and evolving security challenges, including prompt injection attacks, context poisoning, model manipulation, and opaque agent-to-agent communication that are not effectively captured by traditional threat modeling frameworks. In this paper, w

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection
LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data
AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@inproceedings{bandara2025astride,
  title = {{ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications}},
  author = {Eranga Bandara and Amin Hass and Ross Gore and Sachin Shetty and R. Mukkamala and S. Bouk and Xueping Liang and Ng Wee Keong and K. D. Zoysa and A. Withanage and Nilaan Loganathan},
  year = {2025},
  month = dec,
  booktitle = {International Conference on Wireless Communications and Mobile Computing},
  eprint = {2512.04785},
  archivePrefix = {arXiv},
  doi = {10.1109/IWCMC69287.2026.11580105},
  url = {https://www.semanticscholar.org/paper/37c56b578604d3dea4d86ae9bf1a76cdbff5129e}
}