arXiv subjects

Navid Aftabi

Publications and source records attributed to Navid Aftabi.

6 recordsLinked to original sources

arXiv2025

ViSTR-GP: Online Cyberattack Detection via Vision-to-State Tensor Regression and Gaussian Processes in Automated Robotic Operations

Industrial robotic systems are central to automating smart manufacturing operations. Connected and automated factories face growing cybersecurity risks that can potentially cause interruptions and damages to physical operations. Among these attacks, data-integrity attacks often involve sophisticated exploitation of vulnerabilities that enable an attacker to access and manipulate the operational data and are hence difficult to detect with only existing intrusion detection or model-based detection. This paper addresses the challenges in utilizing existing side-channels to detect data-integrity attacks in robotic manufacturing processes by developing an online detection framework, ViSTR-GP, that cross-checks encoder-reported measurements against a vision-based estimate from an overhead camera outside the controller's authority. In this framework, a one-time interactive segmentation initializes SAM-Track to generate per-frame masks. A low-rank tensor-regression surrogate maps each mask to measurements, while a matrix-variate Gaussian process models nominal residuals, capturing temporal structure and cross-joint correlations. A frame-wise test statistic derived from the predictive distribution provides an online detector with interpretable thresholds. We validate the framework on a real-world robotic testbed with synchronized video frame and encoder data, collecting multiple nominal cycles and constructing replay attack scenarios with graded end-effector deviations. Results on the testbed indicate that the proposed framework recovers joint angles accurately and detects data-integrity attacks earlier with more frequent alarms than all baselines. These improvements are most evident in the most subtle attacks. These results show that plants can detect data-integrity attacks by adding an independent physical channel, bypassing the controller's authority, without needing complex instrumentation.

cs.RO↗

arXiv2025

DynaMark: A Reinforcement Learning Framework for Dynamic Watermarking in Industrial Machine Tool Controllers

Industry 4.0's highly networked Machine Tool Controllers (MTCs) are prime targets for replay attacks that use outdated sensor data to manipulate actuators. Dynamic watermarking can reveal such tampering, but current schemes assume linear-Gaussian dynamics and use constant watermark statistics, making them vulnerable to the time-varying, partly proprietary behavior of MTCs. We close this gap with DynaMark, a reinforcement learning framework that models dynamic watermarking as a Markov decision process (MDP). It learns an adaptive policy online that dynamically adapts the covariance of a zero-mean Gaussian watermark using available measurements and detector feedback, without needing system knowledge. DynaMark maximizes a unique reward function balancing control performance, energy consumption, and detection confidence dynamically. We develop a Bayesian belief updating mechanism for real-time detection confidence in linear systems. This approach, independent of specific system assumptions, underpins the MDP for systems with linear dynamics. On a Siemens Sinumerik 828D controller digital twin, DynaMark achieves a reduction in watermark energy by 70% while preserving the nominal trajectory, compared to constant variance baselines. It also maintains an average detection delay equivalent to one sampling interval. A physical stepper-motor testbed validates these findings, rapidly triggering alarms with less control performance decline and exceeding existing benchmarks.

eess.SY↗

arXiv2024

Two-echelon Electric Vehicle Routing Problem in Parcel Delivery: A Literature Review

Multi-echelon parcel delivery systems using electric vehicles (EVs) are crucial for managing urban logistics complexity and promoting sustainability. In multi-echelon systems, particularly within two-stage systems, larger vehicles transport parcels from a central depot to satellite hubs, where smaller EVs pick up the parcels and carry out last-mile deliveries. This system could increase efficiency, reduce emissions, and improve service reliability. The two-echelon electric vehicle routing problem (2E-EVRP), an extension of the traditional two-echelon vehicle routing problem (2E-VRP), addresses EV-specific challenges such as battery constraints and recharging stations to tackle environmental impacts, urban congestion, and e-commerce demands. While effectively reducing costs, energy use, and emissions, the 2E-EVRP faces modeling challenges due to multi-echelon structures, EV limitations, and recharging station selection. This paper systematically reviews 2E-EVRP literature, analyzing key studies. It proposes a classification scheme to categorize the papers based on the problem variants, objectives, constraints, and solution methods. It identifies gaps such as delivery tardiness, environmental trade-offs, multi-objective optimization, multiple depots, split deliveries, and time-dependent travel conditions. Future research directions include aligning models with urban policies, integrating parcel lockers, enabling same-day delivery, and incorporating advanced technologies like autonomous vehicles. Methodological advancements suggest using machine learning, reinforcement learning, and simulation-based approaches to enhance dynamic routing and real-time decision-making. These directions aim to expand the 2E-EVRP applicability, addressing theoretical and practical challenges in sustainable urban logistics for future works.

math.OC↗

arXiv2024

Feed-Forward Neural Networks as a Mixed-Integer Program

Deep neural networks (DNNs) are widely studied in various applications. A DNN consists of layers of neurons that compute affine combinations, apply nonlinear operations, and produce corresponding activations. The rectified linear unit (ReLU) is a typical nonlinear operator, outputting the max of its input and zero. In scenarios like max pooling, where multiple input values are involved, a fixed-parameter DNN can be modeled as a mixed-integer program (MIP). This formulation, with continuous variables representing unit outputs and binary variables for ReLU activation, finds applications across diverse domains. This study explores the formulation of trained ReLU neurons as MIP and applies MIP models for training neural networks (NNs). Specifically, it investigates interactions between MIP techniques and various NN architectures, including binary DNNs (employing step activation functions) and binarized DNNs (with weights and activations limited to $-1,0,+1$). The research focuses on training and evaluating proposed approaches through experiments on handwritten digit classification models. The comparative study assesses the performance of trained ReLU NNs, shedding light on the effectiveness of MIP formulations in enhancing training processes for NNs.

cs.LG↗

arXiv2023

A Variational Autoencoder Framework for Robust, Physics-Informed Cyberattack Recognition in Industrial Cyber-Physical Systems

Cybersecurity of Industrial Cyber-Physical Systems is drawing significant concerns as data communication increasingly leverages wireless networks. A lot of data-driven methods were develope for detecting cyberattacks, but few are focused on distinguishing them from equipment faults. In this paper, we develop a data-driven framework that can be used to detect, diagnose, and localize a type of cyberattack called covert attacks on networked industrial control systems. The framework has a hybrid design that combines a variational autoencoder (VAE), a recurrent neural network (RNN), and a Deep Neural Network (DNN). This data-driven framework considers the temporal behavior of a generic physical system that extracts features from the time series of the sensor measurements that can be used for detecting covert attacks, distinguishing them from equipment faults, as well as localize the attack/fault. We evaluate the performance of the proposed method through a realistic simulation study on a networked power transmission system as a typical example of ICS. We compare the performance of the proposed method with the traditional model-based method to show its applicability and efficacy.

cs.LG↗

arXiv2023

An Integrated Cyber-Physical Risk Assessment Framework for Worst-Case Attacks in Industrial Control Systems

Industrial Control Systems (ICSs) are widely used in critical infrastructures that face various cyberattacks causing physical damage. With the increasing integration of the ICSs and information technology (IT), ensuring the security of ICSs is of paramount importance. In an ICS, cyberattacks exploit vulnerabilities to compromise sensors and controllers, aiming to cause physical damage. Maliciously accessing different components poses varying risks, highlighting the importance of identifying high-risk cyberattacks. This aids in designing effective detection schemes and mitigation strategies. This paper proposes an optimization-based cyber-risk assessment framework that integrates cyber and physical systems of ICSs. The framework models cyberattacks with varying expertise and knowledge by 1) maximizing physical impact in terms of failure time of the physical system, 2) quickly accessing the sensors and controllers in the cyber system while exploiting limited vulnerabilities, 3) avoiding detection in the physical system, and 4) complying with the cyber and physical restrictions. These objectives enable us to jointly model the interactions between the cyber and physical systems and study the critical cyberattacks that cause the highest impact on the physical system under certain resource constraints. Our framework serves as a tool to understand the vulnerabilities of an ICS with a holistic consideration of cyber and physical systems and their interactions and assess the risk of existing detection schemes by generating the worst-case attack strategies. We illustrate and verify the effectiveness of our proposed method in a numerical and a case study. The results show that a worst-case strategic attacker causes almost 19% further acceleration in the failure time of the physical system while remaining undetected compared to a random attacker.

math.OC↗