analiza aiqbench
This research identifies a critical security vulnerability where continual learning mechanisms in IoT and cyber-physical systems inadvertently amplify backdoor persistence through incremental updates. By formalizing an IoT-specific threat model, the study demonstrates how standard adaptation techniques can implant dormant malicious behaviors that activate upon specific triggers during normal operation. The findings underscore the urgent need for specialized security controls to safeguard lifelong learning pipelines against these evolving adversarial tactics in industrial environments.
Continual Backdoor Training in IoT/CPS
arXiv:2606.14987v1 Announce Type: cross Abstract: Internet of Things (IoT) and Cyber-physical systems (CPS) increasingly rely on continual learning (CL) to adapt to evolving environments, device heterogeneity, and concept drift, thereby improving overall utility. While continual adaptation is essential for long-lived IoT deployments where data patterns evolve, it also introduces new security vulnerabilities. In particular, backdoor attacks can exploit incremental updates, replay buffers, and representation reuse to implant persistent malicious behaviors that remain dormant during normal operation but activate upon specific triggers. In this paper, we present a backdoor attack in continual learning used in IoT/CPS systems. To this end, we formalize an IoT/CPS-specific threat model, analyze why continual learning amplifies backdoor persistence in IoT pipelines, and evaluate our technique under varying conditions. Our analysis highlights critical open challenges in securing lifelong learning in IoT/CPS and industrial IoT (IIoT) environments, as well as the need for heightened security controls.
Abstract:Internet of Things (IoT) and Cyber-physical systems (CPS) increasingly rely on continual learning (CL) to adapt to evolving environments, device heterogeneity, and concept drift, thereby improving overall utility. While continual adaptation is essential for long-lived IoT deployments where data patterns evolve, it also introduces new security vulnerabilities. In particular, backdoor attacks can exploit incremental updates, replay buffers, and representation reuse to implant persistent malicious behaviors that remain dormant during normal operation but activate upon specific triggers. In this paper, we present a backdoor attack in continual learning used in IoT/CPS systems. To this end, we formalize an IoT/CPS-specific threat model, analyze why continual learning amplifies backdoor persistence in IoT pipelines, and evaluate our technique under varying conditions. Our analysis highlights critical open challenges in securing lifelong learning in IoT/CPS and industrial IoT (IIoT) environments, as well as the need for heightened security controls.
Cryptography and Security (cs.CR); Machine Learning (cs.LG)
arXiv:2606.14987 [cs.CR]
(or arXiv:2606.14987v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2606.14987 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 241 cuvinte
Subiecte conexe
Anchoring Bias: A Persistent Fairness Backdoor Attack against MLLMs under Continual Learning
arXiv · 25 aug. 2026
Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery
arXiv · 9 sept. 2026
Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in Continual Learning
arXiv · 15 iun. 2026
Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
arXiv · 5 iun. 2026