arXiv subjects

Ruilong Deng

Publications and source records attributed to Ruilong Deng.

14 recordsLinked to original sources

arXiv2026

PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact?

Industrial control systems (ICSs) rely on programmable logic controllers (PLCs) to connect networked computation with physical control. Tool-using large language model (LLM) agents represent an emerging attack threat: can an autonomous agent convert a network-reachable PLC into sustained adverse physical impact? However, existing evaluations focus on digital tasks or individual stages of PLC testing. In ICSs, evaluations that stop at software exploitation, an accepted write, or tool access may therefore mischaracterize physical risk. We present PLCBENCH, to our knowledge, the first real-PLC hardware-in-the-loop (HIL) framework for characterizing this cyber-to-physical capability and its boundaries. It combines vendor-native interaction, commercial PLC execution, closed-loop reduced-order process simulation, and independent outcome verification. A deterministic evaluator applies fixed rules to runner, communication, PLC-object, and process records to assign six hidden diagnostic flags, distinguishing usable PLC interaction, process-linked manipulation, and sustained physical impact. We instantiate PLCBENCH on four commercial PLCs crossed with four closed-loop workloads. Across five LLM families and 240 real-PLC episodes, 75 episodes (31.3%) sustain their respective physical objectives. Stagewise results show that 98 episodes stop before a valid native read, whereas 62 reach a process-linked write but do not sustain the final objective. Notably, richer process observation is associated with an increase in conditional objective attainment after a process-linked write from 44.2% to 64.0%. These measurements localize failure in configured PLC-process deployments and identify intervention points for future defense evaluation. To support reproducibility, we release the safely disclosable PLCBENCH code and a software-only reproduction pipeline through the accompanying artifact.

cs.CR↗

arXiv2026

Hierarchical Sensor-Spoofing Defence Framework for Networked DC Microgrids via Cyber-Physical Coordination

In parallel to the cyber attack that manipulates the reference points of distributed energy resources (DERs) by maliciously accessing the remote monitoring and control system, the vulnerability of voltage/current sensors to electromagnetic interference (EMI) in the physical domain has been widely discussed. Existing research efforts against sensor spoofing attacks can be classified into physical prevention and cyber detection/mitigation. These defence methods each have strengths and weaknesses in balancing cost, security, and performance in a single DER, yet systematic research on their multi-layer efficient coordination across DERs remains limited. Towards this end, this paper proposes a hierarchical framework to detect and mitigate sensor spoofing attacks in networked microgrids (NMGs) via {multi-layer cyber-physical coordination}. It requires only to deploy physical prevention technologies at critical points, i.e., the local points of common coupling (PCC) of MGs, such that cyber detection/mitigation algorithms can be adopted based on the secured sensor readings to counter sensor spoofing attacks in DERs. The framework employs an MG-DER coordinated proactive detection scheme to strategically trigger parameter perturbations, under which the intelligent sensor spoofing attacks can be {effectively} disclosed. Afterwards, mitigation schemes based on MG-DER coordination are activated to recursively and accurately estimate sensor biases. Experiments on a cyber-physical DC NMG testbed confirm the framework's effectiveness across diverse attack scenarios.

eess.SY↗

arXiv2025

Robust Decentralized Quantum Kernel Learning for Noisy and Adversarial Environment

This paper proposes a general decentralized framework for quantum kernel learning (QKL). It has robustness against quantum noise and can also be designed to defend adversarial information attacks forming a robust approach named RDQKL. We analyze the impact of noise on QKL and study the robustness of decentralized QKL to the noise. By integrating robust decentralized optimization techniques, our method is able to mitigate the impact of malicious data injections across multiple nodes. Experimental results demonstrate that our approach maintains high accuracy under noisy quantum operations and effectively counter adversarial modifications, offering a promising pathway towards the future practical, scalable and secure quantum machine learning (QML).

quant-ph↗

arXiv2024

Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices

Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible perturbations in the system inputs, which were generally known as misclassifying attacks. By targeting the real-time processing capability, a new class of latency attacks are reported recently. They exploit new attack surfaces in object detectors by creating a computational bottleneck in the post-processing module, that leads to cascading failure and puts the real-time downstream tasks at risks. In this work, we take an initial attempt to defend against this attack via background-attentive adversarial training that is also cognizant of the underlying hardware capabilities. We first draw system-level connections between latency attack and hardware capacity across heterogeneous GPU devices. Based on the particular adversarial behaviors, we utilize objectness loss as a proxy and build background attention into the adversarial training pipeline, and achieve a reasonable balance between clean and robust accuracy. The extensive experiments demonstrate the defense effectiveness of restoring real-time processing capability from $13$ FPS to $43$ FPS on Jetson Orin NX, with a better trade-off between the clean and robust accuracy.

cs.CV↗

arXiv2024

SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance

Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action sample, thus eliminating the need for retraining on offline data. The frozen offline critic is incorporated with the online target critic weighted by a state-action-adaptive coefficient. This coefficient aims to capture the offline degree of samples at the state-action level, and is updated adaptively during training. In practice, SAMG could be easily integrated with Q-function-based algorithms. Theoretical analysis shows good optimality and lower estimation error. Empirically, SAMG outperforms state-of-the-art O2O RL algorithms on the D4RL benchmark.

cs.LG↗

arXiv2024

Detection-Triggered Recursive Impact Mitigation against Secondary False Data Injection Attacks in Microgrids

The cybersecurity of microgrid has received widespread attentions due to the frequently reported attack accidents against distributed energy resource (DER) manufactures. Numerous impact mitigation schemes have been proposed to reduce or eliminate the impacts of false data injection attacks (FDIAs). Nevertheless, the existing methods either requires at least one neighboring trustworthy agent or may bring in unacceptable cost burdens. This paper aims to propose a detection-triggered recursive impact mitigation scheme that can timely and precisely counter the secondary FDIAs (SFDIAs) against the communication links among DERs. Once triggering attack alarms, the power line current readings will be utilised to observe the voltage bias injections through the physical interconnections among DERs, based on which the current bias injections can be recursively reconstructed from the residuals generated by unknown input observers (UIOs). The attack impacts are eliminated by subtracting the reconstructed bias from the incoming compromised data. The proposed mitigation method can work even in the worst case where all communication links are under SFDIAs and only require extra current sensors. The bias reconstruction performance under initial errors and system noises is theoretically analysed and the reconstruction error is proved to be bounded regardless of the electrical parameters. To avoid deploying current sensors on all power lines, a cost-effective deployment strategy is presented to secure a spanning tree set of communication links that can guarantee the secondary control performance. Extensive validation studies are conducted in MATLAB/SIMULINK and hardware-in-the-loop (HIL) testbeds to validate the proposed method's effectiveness against single/multiple and continuous/discontinuous SFDIAs.

eess.SY↗

arXiv2023

Vulnerability of Machine Learning Approaches Applied in IoT-based Smart Grid: A Review

Machine learning (ML) sees an increasing prevalence of being used in the internet-of-things (IoT)-based smart grid. However, the trustworthiness of ML is a severe issue that must be addressed to accommodate the trend of ML-based smart grid applications (MLsgAPPs). The adversarial distortion injected into the power signal will greatly affect the system's normal control and operation. Therefore, it is imperative to conduct vulnerability assessment for MLsgAPPs applied in the context of safety-critical power systems. In this paper, we provide a comprehensive review of the recent progress in designing attack and defense methods for MLsgAPPs. Unlike the traditional survey about ML security, this is the first review work about the security of MLsgAPPs that focuses on the characteristics of power systems. We first highlight the specifics for constructing the adversarial attacks on MLsgAPPs. Then, the vulnerability of MLsgAPP is analyzed from both the aspects of the power system and ML model. Afterward, a comprehensive survey is conducted to review and compare existing studies about the adversarial attacks on MLsgAPPs in scenarios of generation, transmission, distribution, and consumption, and the countermeasures are reviewed according to the attacks that they defend against. Finally, the future research directions are discussed on the attacker's and defender's side, respectively. We also analyze the potential vulnerability of large language model-based (e.g., ChatGPT) power system applications. Overall, we encourage more researchers to contribute to investigating the adversarial issues of MLsgAPPs.

cs.CR↗

arXiv2023

Enhancing Cyber-Resiliency of DER-based SmartGrid: A Survey

The rapid development of information and communications technology has enabled the use of digital-controlled and software-driven distributed energy resources (DERs) to improve the flexibility and efficiency of power supply, and support grid operations. However, this evolution also exposes geographically-dispersed DERs to cyber threats, including hardware and software vulnerabilities, communication issues, and personnel errors, etc. Therefore, enhancing the cyber-resiliency of DER-based smart grid - the ability to survive successful cyber intrusions - is becoming increasingly vital and has garnered significant attention from both industry and academia. In this survey, we aim to provide a systematical and comprehensive review regarding the cyber-resiliency enhancement (CRE) of DER-based smart grid. Firstly, an integrated threat modeling method is tailored for the hierarchical DER-based smart grid with special emphasis on vulnerability identification and impact analysis. Then, the defense-in-depth strategies encompassing prevention, detection, mitigation, and recovery are comprehensively surveyed, systematically classified, and rigorously compared. A CRE framework is subsequently proposed to incorporate the five key resiliency enablers. Finally, challenges and future directions are discussed in details. The overall aim of this survey is to demonstrate the development trend of CRE methods and motivate further efforts to improve the cyber-resiliency of DER-based smart grid.

eess.SY↗

arXiv2022

A Unified Blockchain-Semantic Framework for Wireless Edge Intelligence Enabled Web 3.0

Web 3.0 enables user-generated contents and user-selected authorities. With decentralized wireless edge computing architectures, Web 3.0 allows users to read, write, and own contents. A core technology that enables Web 3.0 goals is blockchain, which provides security services by recording content in a decentralized and transparent manner. However, the explosion of on-chain recorded contents and the fast-growing number of users cause increasingly unaffordable computing and storage resource consumption. A promising paradigm is to analyze the semantic information of contents that can convey precisely the desired meanings without consuming many resources. In this article, we propose a unified blockchain-semantic ecosystems framework for wireless edge intelligence-enabled Web 3.0. Our framework consists of six key components to exchange semantic demands. We then introduce an Oracle-based proof of semantic mechanism to implement on-chain and off-chain interactions of Web 3.0 ecosystems on semantic verification algorithms while maintaining service security. An adaptive Deep Reinforcement Learning-based sharding mechanism on Oracle is designed to improve interaction efficiency, which can facilitate Web 3.0 ecosystems to deal with varied semantic demands. Finally, a case study is presented to show that the proposed framework can dynamically adjust Oracle settings according to varied semantic demands.

cs.CR↗

arXiv2021

Detecting False Data Injection Attacks in Smart Grids with Modeling Errors: A Deep Transfer Learning Based Approach

Most traditional false data injection attack (FDIA) detection approaches rely on a key assumption, i.e., the power system can be accurately modeled. However, the transmission line parameters are dynamic and cannot be accurately known during operation and thus the involved modeling errors should not be neglected. In this paper, an illustrative case has revealed that modeling errors in transmission lines significantly weaken the detection effectiveness of conventional FDIA approaches. To tackle this issue, we propose an FDIA detection mechanism from the perspective of transfer learning. Specifically, the simulated power system is treated as a source domain, which provides abundant simulated normal and attack data. The real world's running system whose transmission line parameters are unknown is taken as a target domain where sufficient real normal data are collected for tracking the latest system states online. The designed transfer strategy that aims at making full use of data in hand is divided into two optimization stages. In the first stage, a deep neural network (DNN) is built by simultaneously optimizing several well-designed objective terms with both simulated data and real data, and then it is fine-tuned via real data in the second stage. Several case studies on the IEEE 14-bus and 118-bus systems verify the effectiveness of the proposed mechanism.

eess.SP↗

arXiv2021

False Data Injection Attacks and the Distributed Countermeasure in DC Microgrids

In this paper, we consider a hierarchical control based DC microgrid (DCmG) equipped with unknown input observer (UIO) based detectors, where the potential false data injection (FDI) attacks and the distributed countermeasure are investigated. First, we find that the vulnerability of the UIO-based detector originates from the lacked knowledge of true unknown inputs. Zero trace stealthy (ZTS) attacks can be launched by secretly faking the unknown inputs, under which the detection residual will not be altered, and the impact on the DCmG in terms of voltage balancing and current sharing is theoretically analyzed. Then, to mitigate the ZTS attack, we propose an automatic and timely countermeasure based on the average point of common coupling (PCC) voltage obtained from the dynamic average consensus (DAC) estimator. The integrity of the communicated data utilized in DAC estimators is guaranteed via UIO-based detectors, where the DAC parameters are perturbed in a fixed period to be concealed from attackers. Finally, the detection and mitigation performance of the proposed countermeasure is rigorously investigated, and extensive simulations are conducted in Simulink/PLECS to validate the theoretical results.

eess.SY↗

arXiv2020

Deep Reinforcement Learning Based Massive Access Management for Ultra-Reliable Low-Latency Communications

With the rapid deployment of the Internet of Things (IoT), fifth-generation (5G) and beyond 5G networks are required to support massive access of a huge number of devices over limited radio spectrum radio. In wireless networks, different devices have various quality-of-service (QoS) requirements, ranging from ultra-reliable low latency communications (URLLC) to high transmission data rates. In this context, we present a joint energy-efficient subchannel assignment and power control approach to manage massive access requests while maximizing network energy efficiency (EE) and guaranteeing different QoS requirements. The latency constraint is transformed into a data rate constraint which makes the optimization problem tractable before modelling it as a multi-agent reinforcement learning problem. A distributed cooperative massive access approach based on deep reinforcement learning (DRL) is proposed to address the problem while meeting both reliability and latency constraints on URLLC services in massive access scenario. In addition, transfer learning and cooperative learning mechanisms are employed to enable communication links to work cooperatively in a distributed manner, which enhances the network performance and access success probability. Simulation results clearly show that the proposed distributed cooperative learning approach outperforms other existing approaches in terms of meeting EE and improving the transmission success probability in massive access scenario.

eess.SP↗

arXiv2019

Analysis of Moving Target Defense Against False Data Injection Attacks on Power Grid

Recent studies have considered thwarting false data injection (FDI) attacks against state estimation in power grids by proactively perturbing branch susceptances. This approach is known as moving target defense (MTD). However, despite of the deployment of MTD, it is still possible for the attacker to launch stealthy FDI attacks generated with former branch susceptances. In this paper, we prove that, an MTD has the capability to thwart all FDI attacks constructed with former branch susceptances only if (i) the number of branches $l$ in the power system is not less than twice that of the system states $n$ (i.e., $l \geq 2n$, where $n + 1$ is the number of buses); (ii) the susceptances of more than $n$ branches, which cover all buses, are perturbed. Moreover, we prove that the state variable of a bus that is only connected by a single branch (no matter it is perturbed or not) can always be modified by the attacker. Nevertheless, in order to reduce the attack opportunities of potential attackers, we first exploit the impact of the susceptance perturbation magnitude on the dimension of the \emph{stealthy attack space}, in which the attack vector is constructed with former branch susceptances. Then, we propose that, by perturbing an appropriate set of branches, we can minimize the dimension of the \emph{stealthy attack space} and maximize the number of covered buses. Besides, we consider the increasing operation cost caused by the activation of MTD. Finally, we conduct extensive simulations to illustrate our findings with IEEE standard test power systems.

eess.SY↗

arXiv2016

Scheduling of EV Battery Swapping, II: Distributed Solutions

In Part I of this paper we formulate an optimal scheduling problem for battery swapping that assigns to each electric vehicle (EV) a best station to swap its depleted battery based on its current location and state of charge. The schedule aims to minimize a weighted sum of total travel distance and generation cost over both station assignments and power flow variables, subject to EV range constraints, grid operational constraints and AC power flow equations. We propose there a centralized solution based on the second-order cone programming (SOCP) relaxation of optimal power flow (OPF) and generalized Benders decomposition that is suitable when global information is available. In this paper we propose two distributed solutions based on the alternating direction method of multipliers (ADMM) and dual decomposition respectively that are suitable for cases where the distribution grid, battery stations and EVs are managed by separate entities. Our algorithms allow these entities to make individual decisions but coordinate through privacy-preserving information exchanges to jointly solve an approximate version of the joint battery swapping scheduling and OPF problem. We evaluate our algorithms through simulations.

math.OC↗