The ISC International Journal of Information Security

Abstract With the growing adoption of home robots, securing them via efficient intrusion detection systems (IDS) is increasingly vital.
To address the energy and computational constraints of robotic platforms, we adopt a distributed IDS architecture: a resource-rich remote component performs in-depth detection and analysis of operating system logs and network traffic using deep learning, while a lightweight component on the robot controller enables rapid detection.
Remotely estimated attack probabilities are fed into a risk calculator, which then guides a compact ensemble model running on the controller for real-time, risk-based detection. This approach is driven by the need to achieve higher detection performance on the resource-constrained controller.
Rather than relying solely on attack frequency, we enhance detection performance by incorporating self-attention mechanisms to capture dependencies and contextual relationships among attacks.
Evaluated on a custom home robot dataset, our approach demonstrates that modeling attack interdependencies significantly improves detection performance over frequency-only methods. The resulting system achieves high performance without compromising responsiveness, proving that attention-enhanced, risk-aware detection is both feasible and effective in resource-constrained robotic environments.

Abstract Mobile ad-hoc networks (MANETs) have no fixed infrastructure, so all network operations such as routing and packet forwarding are done by the nodes themselves. However, almost all common existing routing protocols basically focus on performance measures regardless of security issues. Since these protocols consider all nodes to be trustworthy, they are prone to serious security threats. Wormhole attack is a kind of such threats against routing processes which is particularly a challenging problem to detect and prevent in MANETs. In this paper, a two-phase detection scheme is proposed to detect and prevent wormhole attacks. First phase checks whether a wormhole tunnel exists on the selected path or not. If there is such a tunnel, the second phase is applied to confirm the existence of the wormhole attack, and locate a malicious node. The proposed detection scheme can appropriately detect all types of this kind of attacks such as in-band and out-of-band ones in different modes such as hidden or exposed, without any need of special hardware or time synchronization. In order to evaluate the performance of the proposed scheme, some various scenarios are simulated in the NS-2 simulator, and different measures are assessed. The results obtained from simulating the proposed scheme and other benchmarks indicate that in most criteria considered in this paper, the proposed scheme outperforms the proposed methods in prior works.