Byzantine-Resilient Locally Optimum Detection Using Collaborative Autonomous Networks
This work addresses the problem of decentralized detection of weak signals in sensor networks, with robustness to adversarial attacks, which is important for security and surveillance applications.
The paper proposes a locally optimum detection scheme for weak radioactive sources and develops a decentralized ADMM-based algorithm for autonomous sensor networks, achieving performance close to centralized clairvoyant detection in low SNR with excellent convergence and scaling. It also introduces a Byzantine-resilient variant robust to data falsification attacks.
In this paper, we propose a locally optimum detection (LOD) scheme for detecting a weak radioactive source buried in background clutter. We develop a decentralized algorithm, based on alternating direction method of multipliers (ADMM), for implementing the proposed scheme in autonomous sensor networks. Results show that algorithm performance approaches the centralized clairvoyant detection algorithm in the low SNR regime, and exhibits excellent convergence rate and scaling behavior (w.r.t. number of nodes). We also devise a low-overhead, robust ADMM algorithm for Byzantine-resilient detection, and demonstrate its robustness to data falsification attacks.