Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2026

Abstract

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges and significantly expands the security attack surface, due to the non-deterministic, learning-driven, and difficult-to-verify nature of LLM behavior. In light of these emerging and unavoidable safety challenges, we argue that such risks should be treated as expected operational conditions rather than exceptional events, necessitating a dedicated incident-response perspective. Consequently, the primary barrier to trustworthy deployment is not further improving model capability but establishing system-level threat monitoring mechanisms that can detect and contextualize security-relevant anomalies after deployment -- an aspect largely underexplored beyond testing or guardrail-based defenses. Accordingly, this position paper advocates systematic and comprehensive monitoring of security threats in LLM-enabled applications as a prerequisite for reliable operation and a foundation for dedicated incident-response frameworks.

Discipline

Artificial Intelligence and Robotics | Information Security

Research Areas

Software and Cyber-Physical Systems

Areas of Excellence

Digital transformation

Publication

Proceedings of the Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS 2026), Sydney, Australia, December 6-12

First Page

1

Last Page

26

Identifier

10.48550/arXiv.2602.19844

City or Country

Australia

Additional URL

https://doi.org/10.48550/arXiv.2602.19844

Download

Share

COinS