Searcharxiv⌕ Search

arXiv subjects

Alireza Mohammadi

Publications and source records attributed to Alireza Mohammadi.

18 recordsLinked to original sources
arXiv2026

Audio Physical Dynamics Inspired Deepfake Detection for Voice Authentication Systems

Voice authentication systems deployed at the network edge face dual threats: a) sophisticated deepfake synthesis attacks and b) control-plane poisoning in distributed federated learning protocols. We present a framework coupling audio physical dynamics deepfake detection with uncertainty-aware in edge learning. The framework fuses interpretable physics features modeling vocal tract dynamics with representations coming from a self-supervised learning module. The representations are then processed via a streamlined Multi-Layer Perceptron backbone, followed by a Bayesian ensemble providing uncertainty estimates. Incorporating audio physical characteristics evaluations and uncertainty estimates of audio samples allows our proposed framework to remain robust to advanced deepfake attacks, while our trust-based aggregation protocol secures the control plane against poisoning in network edge voice authentication systems.

cs.SD↗
arXiv2025

Mitigating Backdoor Triggered and Targeted Data Poisoning Attacks in Voice Authentication Systems

Voice authentication systems remain susceptible to two major threats: backdoor triggered attacks and targeted data poisoning attacks. This dual vulnerability is critical because conventional solutions typically address each threat type separately, leaving systems exposed to adversaries who can exploit both attacks simultaneously. We propose a unified defense framework that effectively addresses both BTA and TDPA. Our framework integrates a frequency focused detection mechanism that flags covert pitch boosting and sound masking backdoor attacks in near real time, followed by a convolutional neural network that addresses TDPA. This dual layered defense approach utilizes multidimensional acoustic features to isolate anomalous signals without requiring costly model retraining. In particular, our PBSM detection mechanism can seamlessly integrate into existing voice authentication pipelines and scale effectively for large scale deployments. Experimental results on benchmark datasets and their compression with the state of the art algorithm demonstrate that our PBSM detection mechanism outperforms the state of the art. Our framework reduces attack success rates to as low as five to fifteen percent while maintaining a recall rate of up to ninety five percent in recognizing TDPA.

cs.CR↗
arXiv2024

Securing Voice Authentication Applications Against Targeted Data Poisoning

Deep neural network-based voice authentication systems are promising biometric verification techniques that uniquely identify biological characteristics to verify a user. However, they are particularly susceptible to targeted data poisoning attacks, where attackers replace legitimate users' utterances with their own. We propose an enhanced framework using realworld datasets considering realistic attack scenarios. The results show that the proposed approach is robust, providing accurate authentications even when only a small fraction (5% of the dataset) is poisoned.

cs.CR↗
arXiv2023

Data-Driven Goal Recognition in Transhumeral Prostheses Using Process Mining Techniques

A transhumeral prosthesis restores missing anatomical segments below the shoulder, including the hand. Active prostheses utilize real-valued, continuous sensor data to recognize patient target poses, or goals, and proactively move the artificial limb. Previous studies have examined how well the data collected in stationary poses, without considering the time steps, can help discriminate the goals. In this case study paper, we focus on using time series data from surface electromyography electrodes and kinematic sensors to sequentially recognize patients' goals. Our approach involves transforming the data into discrete events and training an existing process mining-based goal recognition system. Results from data collected in a virtual reality setting with ten subjects demonstrate the effectiveness of our proposed goal recognition approach, which achieves significantly better precision and recall than the state-of-the-art machine learning techniques and is less confident when wrong, which is beneficial when approximating smoother movements of prostheses.

cs.RO↗
arXiv2023

Sign Gradient Descent Algorithms for Kinetostatic Protein Folding

This paper proposes a sign gradient descent (SGD) algorithm for predicting the three-dimensional folded protein molecule structures under the kinetostatic compliance method (KCM). In the KCM framework, which can be used to simulate the range of motion of peptide-based nanorobots/nanomachines, protein molecules are modeled as a large number of rigid nano-linkages that form a kinematic mechanism under motion constraints imposed by chemical bonds while folding under the kinetostatic effect of nonlinear interatomic force fields. In a departure from the conventional successive kinetostatic fold compliance framework, the proposed SGD-based iterative algorithm in this paper results in convergence to the local minima of the free energy of protein molecules corresponding to their final folded conformations in a faster and more robust manner. KCMbased folding dynamics simulations of the backbone chains of protein molecules demonstrate the effectiveness of the proposed algorithm.

eess.SY↗
arXiv2023

Generation of Time-Varying Impedance Attacks Against Haptic Shared Control Steering Systems

The safety-critical nature of vehicle steering is one of the main motivations for exploring the space of possible cyber-physical attacks against the steering systems of modern vehicles. This paper investigates the adversarial capabilities for destabilizing the interaction dynamics between human drivers and vehicle haptic shared control (HSC) steering systems. In contrast to the conventional robotics literature, where the main objective is to render the human-automation interaction dynamics stable by ensuring passivity, this paper takes the exact opposite route. In particular, to investigate the damaging capabilities of a successful cyber-physical attack, this paper demonstrates that an attacker who targets the HSC steering system can destabilize the interaction dynamics between the human driver and the vehicle HSC steering system through synthesis of time-varying impedance profiles. Specifically, it is shown that the adversary can utilize a properly designed non-passive and time-varying adversarial impedance target dynamics, which are fed with a linear combination of the human driver and the steering column torques. Using these target dynamics, it is possible for the adversary to generate in real-time a reference angular command for the driver input device and the directional control steering assembly of the vehicle. Furthermore, it is shown that the adversary can make the steering wheel and the vehicle steering column angular positions to follow the reference command generated by the time-varying impedance target dynamics using proper adaptive control strategies. Numerical simulations demonstrate the effectiveness of such time-varying impedance attacks, which result in a non-passive and inherently unstable interaction between the driver and the HSC steering system.

eess.SY↗
arXiv2023

Vehicular Applications of Koopman Operator Theory -- A Survey

Koopman operator theory has proven to be a promising approach to nonlinear system identification and global linearization. For nearly a century, there had been no efficient means of calculating the Koopman operator for applied engineering purposes. The introduction of a recent computationally efficient method in the context of fluid dynamics, which is based on the system dynamics decomposition to a set of normal modes in descending order, has overcome this long-lasting computational obstacle. The purely data-driven nature of Koopman operators holds the promise of capturing unknown and complex dynamics for reduced-order model generation and system identification, through which the rich machinery of linear control techniques can be utilized. Given the ongoing development of this research area and the many existing open problems in the fields of smart mobility and vehicle engineering, a survey of techniques and open challenges of applying Koopman operator theory to this vibrant area is warranted. This review focuses on the various solutions of the Koopman operator which have emerged in recent years, particularly those focusing on mobility applications, ranging from characterization and component-level control operations to vehicle performance and fleet management. Moreover, this comprehensive review of over 100 research papers highlights the breadth of ways Koopman operator theory has been applied to various vehicular applications with a detailed categorization of the applied Koopman operator-based algorithm type. Furthermore, this review paper discusses theoretical aspects of Koopman operator theory that have been largely neglected by the smart mobility and vehicle engineering community and yet have large potential for contributing to solving open problems in these areas.

eess.SY↗
arXiv2022

Chetaev Instability Framework for Kinetostatic Compliance-Based Protein Unfolding

Understanding the process of protein unfolding plays a crucial role in various applications such as design of folding-based protein engines. Using the well-established kinetostatic compliance (KCM)-based method for modeling of protein conformation dynamics and a recent nonlinear control theoretic approach to KCM-based protein folding, this paper formulates protein unfolding as a destabilizing control analysis/synthesis problem. In light of this formulation, it is shown that the Chetaev instability framework can be used to investigate the KCM-based unfolding dynamics. In particular, a Chetaev function for analysis of unfolding dynamics under the effect of optical tweezers and a class of control Chetaev functions for synthesizing control inputs that elongate protein strands from their folded conformations are presented. Based on the presented control Chetaev function, an unfolding input is derived from the Artstein-Sontag universal formula and the results are compared against optical tweezer-based unfolding.

eess.SY↗
arXiv2022

Generation of Wheel Lockup Attacks on Nonlinear Dynamics of Vehicle Traction

There is ample evidence in the automotive cybersecurity literature that the car brake ECUs can be maliciously reprogrammed. Motivated by such threat, this paper investigates the capabilities of an adversary who can directly control the frictional brake actuators and would like to induce wheel lockup conditions leading to catastrophic road injuries. This paper demonstrates that the adversary despite having a limited knowledge of the tire-road interaction characteristics has the capability of driving the states of the vehicle traction dynamics to a vicinity of the lockup manifold in a finite time by means of a properly designed attack policy for the frictional brakes. This attack policy relies on employing a predefined-time controller and a nonlinear disturbance observer acting on the wheel slip error dynamics. Simulations under various road conditions demonstrate the effectiveness of the proposed attack policy.

eess.SY↗
arXiv2021

Location-aware Beamforming for MIMO-enabled UAV Communications: An Unknown Input Observer Approach

Numerous communications and networking challenges prevent deploying unmanned aerial vehicles (UAVs) in extreme environments where the existing wireless technologies are mainly ground-focused; and, as a consequence, the air-to-air channel for UAVs is not fully covered. In this paper, a novel spatial estimation for beamforming is proposed to address UAV-based joint sensing and communications (JSC). The proposed spatial estimation algorithm relies on using a delay tolerant observer-based predictor, which can accurately predict the positions of the target UAVs in the presence of uncertainties due to factors such as wind gust. The solution, which uses discrete-time unknown input observers (UIOs), reduces the joint target detection and communication complication notably by operating on the same device and performs reliably in the presence of channel blockage and interference. The effectiveness of the proposed approach is demonstrated using simulation results.

eess.SY↗
arXiv2021

Auditory verbal learning disabilities in patients with mild cog impairment and mild Alzheimer's disease: A clinical study

Learning and memory impairments are common characteristics of individuals with mild cognitive impairment (MCI) and mild Alzheimer's disease (miAD). Early diagnosis of MCI is necessary to prevent recurrence of the disease and developing of miAD. For this purpose, we investigated the components of the Rey Auditory Verbal Learning Test (RAVLT) to explore the auditory-verbal learning (AVL) disabilities in these patients. The AVL of 20 patients with miAD and 30 patients with MCI were compared with 30 cognitively normal controls (CN) using the RAVLT. General cognitive performance assessment was carried out based on the Mini-Mental State Examination (MMSE) score. Finally, Pearson's correlation coefficients were used to evaluate the correlation between the MMSE scores and immediate and delayed recalls, verbal learning and forgetting, and memory recognition. We found that both miAD and MCI subjects were significantly impaired in all components of the RAVLT. Compared to the MCI subjects, miAD patients performed worse on all components of the test. The MCI subjects had significantly lower scores than the CN group. The AVL analysis showed that there were significant differences between the CN and other groups, but the difference between MCI and miAD subjects was not significant. However, there was no difference among the groups in their verbal forgetting scores. It can be concluded that both patients with miAD and MCI were impaired in AVL and our findings confirm that the RAVLT can take a part in the prediction of probable miAD and early evaluation of individuals with subjective memory complaints.

q-bio.NC↗
arXiv2021

Integral Line-of-Sight Path Following Control of Magnetic Helical Microswimmers Subject to Step-Out Frequencies

This paper investigates the problem of straight-line path following for magnetic helical microswimmers. The control objective is to make the helical microswimmer to converge to a straight line without violating the step-out frequency constraint. The proposed feedback control solution is based on an optimal decision strategy (ODS) that is cast as a trust-region subproblem (TRS), i.e., a quadratic program over a sphere. The ODS-based control strategy minimizes the difference between the microrobot velocity and an integral line-of-sight (ILOS)-based reference vector field while respecting the magnetic saturation constraints and ensuring the absolute continuity of the control input. Due to the embedded integral action in the reference vector field, the microswimmer will follow the desired straight line by compensating for the drift effect of the environmental disturbances as well as the microswimmer weight.

eess.SY↗
arXiv2021

Quadratic Optimization-Based Nonlinear Control for Protein Conformation Prediction

Predicting the final folded structure of protein molecules and simulating their folding pathways is of crucial importance for designing viral drugs and studying diseases such as Alzheimer's at the molecular level. To this end, this paper investigates the problem of protein conformation prediction under the constraint of avoiding high-entropy-loss routes during folding. Using the well-established kinetostatic compliance (KCM)-based nonlinear dynamics of a protein molecule, this paper formulates the protein conformation prediction as a pointwise optimal control synthesis problem cast as a quadratic program (QP). It is shown that the KCM torques in the protein folding literature can be utilized for defining a reference vector field for the QP-based control generation problem. The resulting kinetostatic control torque inputs will be close to the KCM-based reference vector field and guaranteed to be constrained by a predetermined bound; hence, high-entropy-loss routes during folding are avoided while the energy of the molecule is decreased.

eess.SY↗
arXiv2019

Improving Brain Magnetic Resonance Image MRI Segmentation via a Novel Algorithm based on Genetic and Regional Growth

Background: Regarding the importance of right diagnosis in medical applications, various methods have been exploited for processing medical images solar. The method of segmentation is used to analyze anal to miscall structures in medical imaging. Objective: This study describes a new method for brain Magnetic Resonance Image (MRI) segmentation via a novel algorithm based on genetic and regional growth. Methods: Among medical imaging methods, brains MRI segmentation is important due to the high contrast of non-intrusive soft tissue and high spatial resolution. Size variations of brain tissues are often accompanied by various diseases such as Alzheimers disease. As our knowledge about the relationship between various brain diseases and deviation of brain anatomy increases, MRI segmentation is exploited as the first step in early diagnosis. In this paper, the regional growth method and auto-mate selection of initial points by genetic algorithm are used to introduce a new method for MRI segmentation. Primary pixels and similarity criterion are automatically by genetic algorithms to maximize the accuracy and validity in image segmentation. Results: By using genetic algorithms and defining the fixed function of image segmentation, the initial points for the algorithm were found. The proposed algorithms are applied to the images and results are manually selected by regional growth in which the initial points were compared. The results showed that the proposed algorithm could reduce segmentation error effectively. Conclusion: The study concluded that the proposed algorithm could reduce segmentation error effectively and help us to diagnose brain diseases.

eess.IV↗
arXiv2018

Dynamics of Insufflated Abdominal Wall Tissue for Magnetically Anchored Surgical Instruments

Magnetically-anchored surgical devices have recently gained attention in abdominal surgery, with the use of magnets to anchor surgical devices onto the insufflated abdominal wall. These anchors have been used to secure passive and active devices, where active device such as robotic manipulators produce motions that would excite the dynamics of the non-rigid abdominal wall. Hence, there is a need to investigate the mechanical dynamics of the abdominal wall tissue in insufflated state, combined with magnetic anchoring, specifically its response to mechanical excitations and the expected disturbances to the operation of the anchored devices. In this paper, loading and unloading tests are performed on a corresponding porcine specimen for dynamics identification. The experiment setup was constructed to emulate the insufflated state of the abdomen with the magnetically anchored mechanism. The tissue responses during unloading are captured and approximated with a general numerical model, which is in turn used for the dynamic analysis of the tissue using Bode plot. The results showed that in such stretched and compressed state, the steady state displacement of the tissue is approximately zero. The maximum transient error was found to be 1mm in displacement using a high magnetic anchoring force. Significant attenuation of the disturbances due to the high stiffness and damping of the abdominal wall, was observed from 100rad/s in the frequency response. If a robotic manipulator was attached to the anchoring device, the typical operating frequency of movements would still produce unattenuated disturbances. It is expected that some error compensation through suitable control strategies is required. These outcomes establish the basis for the controller design and the design specification of the active magnetically-anchored surgical devices for minimal disturbance impact onto the abdominal wall tissue.

physics.med-ph↗
arXiv2018

Dynamic Virtual Holonomic Constraints for Stabilization of Closed Orbits in Underactuated Mechanical Systems

This article investigates the problem of enforcing a virtual holonomic constraint (VHC) on a mechanical system with degree of underactuation one while simultaneously stabilizing a closed orbit on the constraint manifold. This problem, which to date is open, arises when designing controllers to induce complex repetitive motions in robots. In this paper, we propose a solution which relies on the parameterization of the VHC by the output of a double-integrator. While the original control inputs are used to enforce the VHC, the control input of the double-integrator is designed to asymptotically stabilize the closed orbit and make the state of the double-integrator converge to zero. The proposed design is applied to the problem of making a PVTOL aircraft follow a circle on the vertical plane with a desired speed profile, while guaranteeing that the aircraft does not roll over for suitable initial conditions.

math.DS↗
arXiv2017

On the Lagrangian Structure of Reduced Dynamics Under Virtual Holonomic Constraints

This paper investigates a class of Lagrangian control systems with $n$ degrees-of-freedom (DOF) and n-1 actuators, assuming that $n-1$ virtual holonomic constraints have been enforced via feedback, and a basic regularity condition holds. The reduced dynamics of such systems are described by a second-order unforced differential equation. We present necessary and sufficient conditions under which the reduced dynamics are those of a mechanical system with one DOF and, more generally, under which they have a Lagrangian structure. In both cases, we show that typical solutions satisfying the virtual constraints lie in a restricted class which we completely characterize.

math.DS↗