![[2602.13062] Backdoor Attacks on Contrastive Continual Learning for IoT Systems](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.13062] Backdoor Attacks on Contrastive Continual Learning for IoT Systems
Summary
This paper analyzes backdoor attacks on contrastive continual learning (CCL) in IoT systems, highlighting vulnerabilities and proposing defense strategies.
Why It Matters
As IoT systems increasingly rely on continual learning, understanding and mitigating backdoor attacks is crucial for ensuring security and reliability. This research provides insights into the unique challenges posed by CCL in IoT environments, emphasizing the need for robust defense mechanisms.
Key Takeaways
- Backdoor attacks can exploit vulnerabilities in contrastive continual learning for IoT systems.
- The paper introduces a taxonomy for understanding embedding-level attacks specific to IoT.
- Defense strategies must consider the constraints of IoT, such as limited memory and edge computing.
- CCL enhances IoT adaptability but may introduce persistent security threats if not secured.
- Comparative analysis of vulnerabilities across learning paradigms is provided.
Computer Science > Machine Learning arXiv:2602.13062 (cs) [Submitted on 13 Feb 2026] Title:Backdoor Attacks on Contrastive Continual Learning for IoT Systems Authors:Alfous Tim, Kuniyilh Simi D View a PDF of the paper titled Backdoor Attacks on Contrastive Continual Learning for IoT Systems, by Alfous Tim and 1 other authors View PDF HTML (experimental) Abstract:The Internet of Things (IoT) systems increasingly depend on continual learning to adapt to non-stationary environments. These environments can include factors such as sensor drift, changing user behavior, device aging, and adversarial dynamics. Contrastive continual learning (CCL) combines contrastive representation learning with incremental adaptation, enabling robust feature reuse across tasks and domains. However, the geometric nature of contrastive objectives, when paired with replay-based rehearsal and stability-preserving regularization, introduces new security vulnerabilities. Notably, backdoor attacks can exploit embedding alignment and replay reinforcement, enabling the implantation of persistent malicious behaviors that endure through updates and deployment cycles. This paper provides a comprehensive analysis of backdoor attacks on CCL within IoT systems. We formalize the objectives of embedding-level attacks, examine persistence mechanisms unique to IoT deployments, and develop a layered taxonomy tailored to IoT. Additionally, we compare vulnerabilities across various learning paradigms and evaluate defe...
