Ahmed Elliethy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ahmed Elliethy has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Gaurav Sharma
Department of Electrical and Computer Engineering, University of Rochester, Rochester, USA
12 shared publications - Hussein A. Aly
Military Technical College
12 shared publications - Amr Abdelaziz
Military Technical College
4 shared publications - Hassan Mohamed
Computer Engineering, Military Technical College, Cairo, Egypt
3 shared publications - Mohamed Awad
Military Technical College, Cairo, Egypt
3 shared publications - Thomas Aaron Gulliver
Department of Electrical and Computer Engineering, University of Victoria, Victoria, BC, Canada
3 shared publications
Latest Publications
- Open Access
- 25 June 2026
- Published by Elsevier in SSRN Electronic Journal
Submodular Set Cover-Based Coreset Feature Selection for Efficient Intrusion Detection in IoT Networks
The rapid growth of network trac and the high dimensionality of intrusion detection datasets pose major challenges for ecient and accurate intrusion detection. Traditional feature selection methods often rely on heuristic or statistical measures that fail to guarantee representative coverage of the underlying feature space. This paper proposes a principled feature selection framework grounded in submodular optimization. Specically, we formulate the feature selection problem as a submodular set cover task and introduce the Coreset Greedy-Based Feature Selection (CGFS) algorithm to construct compact yet highly representative feature subsets. The proposed CGFS algorithm leverages the facility location function to quantify feature representativeness and applies a greedy selection process that achieves a provable logarithmic approximation bound to the optimal subset. To ensure scalability, we incorporate several eciency-oriented strategies to mitigate the computational cost of large-scale similarity evaluations inherent in the submodular set cover formulation, including pre-normalized inner-product similarity computation, approximate nearest neighbor search via FAISS, and a lazy greedy selection mechanism. Experimental results on ve benchmark IDS datasets demonstrate that CGFS signicantly reduces the number of features while preserving or even improving detection performance, oering a strong balance between accuracy, generalizability, and computational eciency. The source code is available on GitHub.
- 25 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSubmodular Set Cover-Based Coreset Feature Selection for Efficient Intrusion Detection in IoT Networks
The rapid growth of network trac and the high dimensionality of intrusion detection datasets pose major challenges for ecient and accurate intrusion detection. Traditional feature selection methods often rely on heuristic or statistical measures that fail to guarantee representative coverage of the underlying feature space. This paper proposes a principled feature selection framework grounded in submodular optimization. Specically, we formulate the feature selection problem as a submodular set cover task and introduce the Coreset Greedy-Based Feature Selection (CGFS) algorithm to construct compact yet highly representative feature subsets. The proposed CGFS algorithm leverages the facility location function to quantify feature representativeness and applies a greedy selection process that achieves a provable logarithmic approximation bound to the optimal subset. To ensure scalability, we incorporate several eciency-oriented strategies to mitigate the computational cost of large-scale similarity evaluations inherent in the submodular set cover formulation, including pre-normalized inner-product similarity computation, approximate nearest neighbor search via FAISS, and a lazy greedy selection mechanism. Experimental results on ve benchmark IDS datasets demonstrate that CGFS signicantly reduces the number of features while preserving or even improving detection performance, oering a strong balance between accuracy, generalizability, and computational eciency. The source code is available on GitHub.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35  (10577149) , 2407-2422
A Multi-Level Self-Distillation-Based Unified Tracker for Efficient RGB-T Tracking
RGB-Thermal (RGB-T) tracking enhances visual tracking robustness by combining RGB and thermal infrared (TIR) modalities, addressing limitations of RGB-only trackers under challenging conditions such as low light and appearance variations. However, most existing RGB-T trackers rely on complex fusion modules or modality-specific architectures, sacrificing efficiency for performance. In this paper, we propose a novel Multi-level Self-Distillation (MSD) framework that adapts a one-stream RGB tracker to the RGB-T setting without modifying the network architecture or adding any extra parameters. RGB and TIR inputs are jointly processed through a shared backbone, and training is guided by a combination of self-supervised and supervised objectives to enhance cross-modal feature representation. The self-supervised component includes a contrastive loss that aligns semantically consistent regions across template-search pairs, as well as a modality-gap alignment loss that reduces discrepancies between RGB and TIR features. These internal signals complement task-driven supervision, including an intermediate focal loss that strengthens early localization by enhancing shallow and mid-level features, modality-specific losses that preserve distinctive cues under partial modality degradation, and a fused tracking loss that drives final bounding box prediction. Comprehensive evaluations on LasHeR, RGBT234, and GTOT benchmarks demonstrate that MSD achieves state-of-the-art tracking accuracy while maintaining the computational efficiency of the original RGB tracker. Our work establishes a new paradigm in multi-modal tracking by demonstrating that optimized training strategies can outperform complex architectural modifications, offering significant practical advantages for real-world deployment.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35  (10577149) , 2407-2422
A Multi-Level Self-Distillation-Based Unified Tracker for Efficient RGB-T Tracking
RGB-Thermal (RGB-T) tracking enhances visual tracking robustness by combining RGB and thermal infrared (TIR) modalities, addressing limitations of RGB-only trackers under challenging conditions such as low light and appearance variations. However, most existing RGB-T trackers rely on complex fusion modules or modality-specific architectures, sacrificing efficiency for performance. In this paper, we propose a novel Multi-level Self-Distillation (MSD) framework that adapts a one-stream RGB tracker to the RGB-T setting without modifying the network architecture or adding any extra parameters. RGB and TIR inputs are jointly processed through a shared backbone, and training is guided by a combination of self-supervised and supervised objectives to enhance cross-modal feature representation. The self-supervised component includes a contrastive loss that aligns semantically consistent regions across template-search pairs, as well as a modality-gap alignment loss that reduces discrepancies between RGB and TIR features. These internal signals complement task-driven supervision, including an intermediate focal loss that strengthens early localization by enhancing shallow and mid-level features, modality-specific losses that preserve distinctive cues under partial modality degradation, and a fused tracking loss that drives final bounding box prediction. Comprehensive evaluations on LasHeR, RGBT234, and GTOT benchmarks demonstrate that MSD achieves state-of-the-art tracking accuracy while maintaining the computational efficiency of the original RGB tracker. Our work establishes a new paradigm in multi-modal tracking by demonstrating that optimized training strategies can outperform complex architectural modifications, offering significant practical advantages for real-world deployment.
- Open Access
- 10 December 2025
- Published by Springer Nature in Research Square
RRH-RL: Recursive Receding Horizon Deep Reinforcement Learning for End-to-End Robot Navigation in Mapless Harsh Environments
This paper presents RRH-RL, a Recursive Receding Horizon Reinforcement Learning approach for end-to-end mobile robot navigation in mapless, harsh environments. Navigation in such conditions poses multiple challenges, including partial observability, short-sighted decision-making, trap avoidance, and energy inefficiency. RRH-RL addresses these by predicting a horizon of future actions at each step, executing the first, and recursively embedding the rest into subsequent observations to maintain temporal consistency and to produce energy-efficient motion. A probabilistic costmap—updated via Bayesian filtering and belief propagation (BP)—serves as spatial memory to avoid revisiting dead ends and being trapped. A projection-based mechanism estimates future sensor observations, enabling accurate foresight-driven reward shaping. Experiments in high-fidelity simulations across diverse harsh environments maps show that RRH-RL significantly outperforms state-of-the-art approaches, achieving up to 7.58\% higher success rate, 9.86\% shorter path length, 22.06\% smoother motion, and 20.67\% lower energy consumption, compared to the next best approach. Additionally, ablation studies are performed to validate the contribution of horizon length, recursive action embedding, and the BP to overall performance. The full source code is available on GitHub.
- 10 December 2025
- Published by Springer Nature in Research Square
Open AccessRRH-RL: Recursive Receding Horizon Deep Reinforcement Learning for End-to-End Robot Navigation in Mapless Harsh Environments
This paper presents RRH-RL, a Recursive Receding Horizon Reinforcement Learning approach for end-to-end mobile robot navigation in mapless, harsh environments. Navigation in such conditions poses multiple challenges, including partial observability, short-sighted decision-making, trap avoidance, and energy inefficiency. RRH-RL addresses these by predicting a horizon of future actions at each step, executing the first, and recursively embedding the rest into subsequent observations to maintain temporal consistency and to produce energy-efficient motion. A probabilistic costmap—updated via Bayesian filtering and belief propagation (BP)—serves as spatial memory to avoid revisiting dead ends and being trapped. A projection-based mechanism estimates future sensor observations, enabling accurate foresight-driven reward shaping. Experiments in high-fidelity simulations across diverse harsh environments maps show that RRH-RL significantly outperforms state-of-the-art approaches, achieving up to 7.58\% higher success rate, 9.86\% shorter path length, 22.06\% smoother motion, and 20.67\% lower energy consumption, compared to the next best approach. Additionally, ablation studies are performed to validate the contribution of horizon length, recursive action embedding, and the BP to overall performance. The full source code is available on GitHub.
- 6 February 2025
- Published by Taylor & Francis in Journal of Control and Decision
- p. 1-18
Accelerating genetic optimisation of nonlinear model predictive control by learning optimal search space size
- 6 February 2025
- Published by Taylor & Francis in Journal of Control and Decision
- p. 1-18
Accelerating genetic optimisation of nonlinear model predictive control by learning optimal search space size
- 23 January 2025
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 89
Information-theoretic bounds for steganography in visual multimedia
- 23 January 2025
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 89
Information-theoretic bounds for steganography in visual multimedia
- Open Access
- 27 March 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84  (8) , 5001-5024
Real-time motion estimation based video steganography with preserved consistency and local optimality
This paper introduces a novel steganographic technique for H.264 video that achieves an outstanding performance against state-of-the-art steganalysis techniques while maintaining real-time encoding performance constraints. The proposed technique embeds the secret message by altering the motion vectors (MVs) while preserving their local optimality and consistency feature to withstand the recently emerged steganalysis methods. Thanks to its macro-block (MB) basis architecture, the proposed technique satisfies the real-time constraints, eliminating the need to wait for the whole frame or group of pictures (GOP) and avoiding the need to perform any additional re-encoding step(s). Additionally, altering the MVs is performed in the motion estimation (ME) sub-pixel-refinement stage through a rule-based scheme that ensures each MB’s compatibility for embedding without detection by the aforementioned steganalysis methods. The proposed technique is integrated with the OpenH264 real-time video encoder and evaluated on widely used video sequences. The results prove that the proposed technique achieves a significant security performance against the steganalysis methods while maintaining an acceptable embedding rate, outperforming other state-of-the-art MV-based steganographic methods in real-time constrained environments. The proposed technique adds about $$1-2\%$$ overhead beyond the encoder running time. The source code is publicly available here: https://github.com/HassanMohamedGit/OpenH264-RealTime-steg.- 27 March 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84  (8) , 5001-5024
Open AccessReal-time motion estimation based video steganography with preserved consistency and local optimality
This paper introduces a novel steganographic technique for H.264 video that achieves an outstanding performance against state-of-the-art steganalysis techniques while maintaining real-time encoding performance constraints. The proposed technique embeds the secret message by altering the motion vectors (MVs) while preserving their local optimality and consistency feature to withstand the recently emerged steganalysis methods. Thanks to its macro-block (MB) basis architecture, the proposed technique satisfies the real-time constraints, eliminating the need to wait for the whole frame or group of pictures (GOP) and avoiding the need to perform any additional re-encoding step(s). Additionally, altering the MVs is performed in the motion estimation (ME) sub-pixel-refinement stage through a rule-based scheme that ensures each MB’s compatibility for embedding without detection by the aforementioned steganalysis methods. The proposed technique is integrated with the OpenH264 real-time video encoder and evaluated on widely used video sequences. The results prove that the proposed technique achieves a significant security performance against the steganalysis methods while maintaining an acceptable embedding rate, outperforming other state-of-the-art MV-based steganographic methods in real-time constrained environments. The proposed technique adds about $$1-2\%$$ overhead beyond the encoder running time. The source code is publicly available here: https://github.com/HassanMohamedGit/OpenH264-RealTime-steg. - 25 September 2023
- Published by Springer Nature in Control Theory and Technology
- Vol. 21  (4) , 555-570
Fast adaptive regression-based model predictive control
- 25 September 2023
- Published by Springer Nature in Control Theory and Technology
- Vol. 21  (4) , 555-570
Fast adaptive regression-based model predictive control
- Open Access
Fast Adaptive Regression-based Model Predictive Control
Model predictive control (MPC) is an optimal control method that predicts the future states of the system being controlled and estimates the optimal control inputs that drive the predicted states to the required reference. The computations of the MPC are performed at pre-determined sample instances over a finite time horizon. The number of sample instances and the horizon length determine the performance of the MPC and its computational cost. A long horizon with a large sample count allows the MPC to better estimate the inputs when the states have rapid changes over time, which results in better performance but at the expense of high computational cost. However, this long horizon is not always necessary, especially for slowly-varying states. In this case, a short horizon with less sample count is preferable as the same MPC performance can be obtained but at a fraction of the computational cost. In this paper, we propose an adaptive regression-based MPC that predicts the best minimum horizon length and the sample count from several features extracted from the time-varying changes of the states. The proposed technique builds a synthetic dataset using the system model and utilizes the dataset to train a support vector regressor that performs the prediction. The proposed technique is experimentally compared with several state-of-the-art techniques on both linear and non-linear models. The proposed technique shows a superior reduction in computational time with a reduction of about 35-65\% compared with the other techniques without introducing a noticeable loss in performance.
Open AccessFast Adaptive Regression-based Model Predictive Control
Model predictive control (MPC) is an optimal control method that predicts the future states of the system being controlled and estimates the optimal control inputs that drive the predicted states to the required reference. The computations of the MPC are performed at pre-determined sample instances over a finite time horizon. The number of sample instances and the horizon length determine the performance of the MPC and its computational cost. A long horizon with a large sample count allows the MPC to better estimate the inputs when the states have rapid changes over time, which results in better performance but at the expense of high computational cost. However, this long horizon is not always necessary, especially for slowly-varying states. In this case, a short horizon with less sample count is preferable as the same MPC performance can be obtained but at a fraction of the computational cost. In this paper, we propose an adaptive regression-based MPC that predicts the best minimum horizon length and the sample count from several features extracted from the time-varying changes of the states. The proposed technique builds a synthetic dataset using the system model and utilizes the dataset to train a support vector regressor that performs the prediction. The proposed technique is experimentally compared with several state-of-the-art techniques on both linear and non-linear models. The proposed technique shows a superior reduction in computational time with a reduction of about 35-65\% compared with the other techniques without introducing a noticeable loss in performance.
- Open Access
- 27 April 2023
- Published by PeerJ in PeerJ Computer Science
- Vol. 9, e1359
Neural noiseprint transfer: a generic noiseprint-based counter forensics framework
A noiseprint is a camera-related artifact that can be extracted from an image to serve as a powerful tool for several forensic tasks. The noiseprint is built with a deep learning data-driven approach that is trained to produce unique noise residuals with clear traces of camera-related artifacts. This data-driven approach results in a complex relationship that governs the noiseprint with the input image, making it challenging to attack. This article proposes a novel neural noiseprint transfer framework for noiseprint-based counter forensics. Given an authentic image and a forged image, the proposed framework synthesizes a newly generated image that is visually imperceptible to the forged image, but its noiseprint is very close to the noiseprint of the authentic one, to make it appear as if it is authentic and thus renders the noiseprint-based forensics ineffective. Based on deep content and noiseprint representations of the forged and authentic images, we implement the proposed framework in two different approaches. The first is an optimization-based approach that synthesizes the generated image by minimizing the difference between its content representation with the content representation of the forged image while, at the same time, minimizing the noiseprint representation difference from the authentic one. The second approach is a noiseprint injection-based approach, which first trains a novel neural noiseprint-injector network that can inject the noiseprint of an image into another one. Then, the trained noiseprint-injector is used to inject the noiseprint from the authentic image into the forged one to produce the generated image. The proposed approaches are generic and do not require training for specific images or camera models. Both approaches are evaluated on several datasets against two common forensic tasks: the forgery localization and camera source identification tasks. In the two tasks, the proposed approaches are able to significantly reduce several forensic accuracy scores compared with two noiseprint-based forensics methods while at the same time producing high-fidelity images. On the DSO-1 dataset, the reduction in the forensic accuracy scores has an average of 75%, while the produced images have an average PSNR of 31.5 dB and SSIM of 0.9. The source code of the proposed approaches is available on GitHub (https://github.com/ahmed-elliethy/nnt).
- 27 April 2023
- Published by PeerJ in PeerJ Computer Science
- Vol. 9, e1359
Open AccessNeural noiseprint transfer: a generic noiseprint-based counter forensics framework
A noiseprint is a camera-related artifact that can be extracted from an image to serve as a powerful tool for several forensic tasks. The noiseprint is built with a deep learning data-driven approach that is trained to produce unique noise residuals with clear traces of camera-related artifacts. This data-driven approach results in a complex relationship that governs the noiseprint with the input image, making it challenging to attack. This article proposes a novel neural noiseprint transfer framework for noiseprint-based counter forensics. Given an authentic image and a forged image, the proposed framework synthesizes a newly generated image that is visually imperceptible to the forged image, but its noiseprint is very close to the noiseprint of the authentic one, to make it appear as if it is authentic and thus renders the noiseprint-based forensics ineffective. Based on deep content and noiseprint representations of the forged and authentic images, we implement the proposed framework in two different approaches. The first is an optimization-based approach that synthesizes the generated image by minimizing the difference between its content representation with the content representation of the forged image while, at the same time, minimizing the noiseprint representation difference from the authentic one. The second approach is a noiseprint injection-based approach, which first trains a novel neural noiseprint-injector network that can inject the noiseprint of an image into another one. Then, the trained noiseprint-injector is used to inject the noiseprint from the authentic image into the forged one to produce the generated image. The proposed approaches are generic and do not require training for specific images or camera models. Both approaches are evaluated on several datasets against two common forensic tasks: the forgery localization and camera source identification tasks. In the two tasks, the proposed approaches are able to significantly reduce several forensic accuracy scores compared with two noiseprint-based forensics methods while at the same time producing high-fidelity images. On the DSO-1 dataset, the reduction in the forensic accuracy scores has an average of 75%, while the produced images have an average PSNR of 31.5 dB and SSIM of 0.9. The source code of the proposed approaches is available on GitHub (https://github.com/ahmed-elliethy/nnt).
- Open Access
- 19 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Information-Theoretic Bounds for Steganography in Multimedia
Steganography in multimedia aims to embed secret data into an innocent looking multimedia cover object. This embedding introduces some distortion to the cover object and produces a corresponding stego object. The embedding distortion is measured by a cost function that determines the detection probability of the existence of the embedded secret data. A cost function related to the maximum embedding rate is typically employed to evaluate a steganographic system. In addition, the distribution of multimedia sources follows the Gibbs distribution which is a complex statistical model that restricts analysis. Thus, previous multimedia steganographic approaches either assume a relaxed distribution or presume a proposition on the maximum embedding rate and then try to prove it is correct. Conversely, this paper introduces an analytic approach to determining the maximum embedding rate in multimedia cover objects through a constrained optimization problem concerning the relationship between the maximum embedding rate and the probability of detection by any steganographic detector. The KL-divergence between the distributions for the cover and stego objects is used as the cost function as it upper bounds the performance of the optimal steganographic detector. An equivalence between the Gibbs and correlated-multivariate-quantized-Gaussian distributions is established to solve this optimization problem. The solution provides an analytic form for the maximum embedding rate in terms of the WrightOmega function. Moreover, it is proven that the maximum embedding rate is in agreement with the commonly used Square Root Law (SRL) for steganography, but the solution presented here is more accurate. Finally, the theoretical results obtained are verified experimentally.
- 19 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessInformation-Theoretic Bounds for Steganography in Multimedia
Steganography in multimedia aims to embed secret data into an innocent looking multimedia cover object. This embedding introduces some distortion to the cover object and produces a corresponding stego object. The embedding distortion is measured by a cost function that determines the detection probability of the existence of the embedded secret data. A cost function related to the maximum embedding rate is typically employed to evaluate a steganographic system. In addition, the distribution of multimedia sources follows the Gibbs distribution which is a complex statistical model that restricts analysis. Thus, previous multimedia steganographic approaches either assume a relaxed distribution or presume a proposition on the maximum embedding rate and then try to prove it is correct. Conversely, this paper introduces an analytic approach to determining the maximum embedding rate in multimedia cover objects through a constrained optimization problem concerning the relationship between the maximum embedding rate and the probability of detection by any steganographic detector. The KL-divergence between the distributions for the cover and stego objects is used as the cost function as it upper bounds the performance of the optimal steganographic detector. An equivalence between the Gibbs and correlated-multivariate-quantized-Gaussian distributions is established to solve this optimization problem. The solution provides an analytic form for the maximum embedding rate in terms of the WrightOmega function. Moreover, it is proven that the maximum embedding rate is in agreement with the commonly used Square Root Law (SRL) for steganography, but the solution presented here is more accurate. Finally, the theoretical results obtained are verified experimentally.