Skip to content
Preprint

MDRC: A Deployable State-Recovery Defense for Traffic Signal Control under Sensor Corruption

Sep 2026 · 0 citations · 51 references
Computer Science

TL;DR

MDRC (Meta-Diffusion-based framework for Resilient traffic signal Control against adversarial attacks and sensor failures), a post-detection state-recovery defense inserted between sensing and control that reconstructs trustworthy traffic states before they are consumed by the controller.

Abstract

Traffic Signal Control (TSC) is a safety-critical cyber-physical system that relies on real-time sensing. Corrupted observations caused by adversarial perturbations or sensor failures can propagate from the sensing layer into the controller and degrade traffic efficiency. Existing robust Reinforcement Learning (RL)-based TSC methods often suffer from limited cross-city generalization, high inference latency, and weak recovery under partial observability. We present MDRC (Meta-Diffusion-based framework for Resilient traffic signal Control against adversarial attacks and sensor failures), a post-detection state-recovery defense inserted between sensing and control. MDRC reconstructs trustworthy traffic states before they are consumed by the controller. It combines Denoising Diffusion Implicit Models (DDIM) for efficient state recovery with Reptile meta-learning for a transferable initialization across cities. We provide an optimization-based view of the DDIM recovery dynamics and establish a recovery-error bound that separates score approximation, numerical discretization, and initialization mismatch. Across seven real-world-derived CityFlow benchmarks, MDRC reduces Average Travel Time by 6.77% under stochastic and policy-aware attacks and by 12.75% under structured sensor loss, while improving state-recovery fidelity. We further evaluate 3,600 seconds of real roadside measurements with 50% of detector channels disabled and integrate MDRC into a hardware-in-the-loop traffic-signal stack. Over a 9.16-hour run with 32,389 sensing/control cycles, the system achieves 99.79% decision availability, produces no out-of-plan recommendations, and requires approximately 38 ms of component-wise processing per one-second control interval.

View source

Similar papers

#reinforcement learning Open access Sep 2026

A Case Study on the Robustness of Traffic Signal Control from a Data Science Perspective: The RobustLight Diffusion Reinforcement Learning Framework

Damaged sensor data, often caused by noise interference and data loss, impairs the decision-making accuracy of Deep Reinforcement Learning (DRL) traffic signal control models. This paper takes RobustLight (ICML 2025) as the core case and analyzes it from a data science perspective. We introduce DRL-based traffic signal...

Pei-Yu Qian · 0 citations
Open access 2026

Adaptive Defense Optimization Under Intelligent Data Poisoning Attacks in Industrial Control System

As industrial control systems (ICSs) 4.0 evolve into open and networked environments, they face a critical challenge in maintaining robust closed-loop operation under feedback streams that are asynchronous, unreliable, and subject to adversarial data poisoning. This paper proposes a detection-aware stochastic optimizat...

Xiao Cai, Yan-Bin Sun, Hui Lu et al. · 0 citations
Open access 2026

Cyberattack-Resilient Data Assimilation for Smart IoT Infrastructures: Sparse Attack Reconstruction and Certified State Estimation

Smart Internet-of-Things (IoT) infrastructures infer physical states from heterogeneous, delayed and noisy sensor streams. Their dependence on networked measurements creates a structural vulnerability: a false data injection adversary can alter a small subset of observations while preserving the superficial statistical...

Kaarina Nakale · 0 citations
Conference Open access Oct 2026

Blockchain-Anchored Detection and Recovery for Resilient Reinforcement Learning-Based Cyber-Physical Systems

Reinforcement learning (RL) controllers in cyber-physical systems (CPS) assume that sensor observations describe the true plant state, yet replay, sensor-drift, and false-data-injection (FDI) attacks can corrupt the observation stream at inference time, and detection alone does not tell the controller what to use after...

I. Khan, Maliha Hossain, M. Rahman et al. · 0 citations
Review Open access Aug 2026

Distributed algorithms for filtering, estimation, and fault detection over cyber–physical-systems: A tutorial and survey

This survey provides overview of distributed estimation, filtering, and fault detection techniques in the context of cyber-physical systems (CPS). To establish a strong foundation, we first define essential aspects of linear dynamical systems and related graph theoretic concepts, emphasizing observability conditions th...

Mohammadreza Doostmohammadian, Mahdi Shamsi, Hadi Zayyani et al. · 0 citations
2026

Adaptive Learning-Based Resilient Automation for Switched Systems Under FDI Attacks and Actuator Faults

Automated systems operating across multiple modes increasingly rely on networked sensing and feedback, which makes them vulnerable to abrupt actuator faults and false-data-injection (FDI) attacks. This paper studies resilient estimation and control for continuous-time switched automation systems under these two coupled...

Yong-Hong Chen, Qi-Long Xie, Mei Yan et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.