Heba Khdr
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Heba Khdr has a total of 86 co-authors. Here are the top co-authors by number of shared publications:
- Jorg Henkel
Karlsruhe Institute of Technology (KIT), Chair for Embedded Systems (CES), Karlsruhe, Germany
18 shared publications Jorg Henkel
Karlsruhe Institute of Technology, Karlsruhe, Germany
5 shared publications- Hussam Amrouch
Technical University of Munich
4 shared publications - Mohammed Bakr Sikal
Chair for Embedded Systems, Karlsruhe Institute of Technology, Karlsruhe, Germany
4 shared publications - Mohsen Ansari
Sharif University of Technology
4 shared publications - Sepideh Safari
School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran
4 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 18 (5) , 456-459
Securing Vision Transformers Against Adversarial Attacks via Input Purification in Trusted Execution Environments
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 18 (5) , 456-459
Securing Vision Transformers Against Adversarial Attacks via Input Purification in Trusted Execution Environments
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 18 (5) , 328-331
SFLGuard: Model Poisoning Mitigation in Split Federated Learning via Activation-Level Attestation
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 18 (5) , 328-331
SFLGuard: Model Poisoning Mitigation in Split Federated Learning via Activation-Level Attestation
- Open Access
- 14 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
ISA-Agnostic WCET Co-Analysis of Mixed Hardware/Software Designs
Ensuring safety-critical systems meet timing constraints is essential in aerospace, automotive, and industrial control. Failure can be catastrophic, making worst-case execution time (WCET) determination crucial. Most existing WCET tools require a pre-existing timing model for the target processor and an instruction set architecture (ISA) specific control flow reconstruction algorithm. However, in hardware/software co-design environments, where both ISA and timing behavior evolve, neither a timing model nor the control flow reconstruction algorithm may exist. We introduce a novel method for computing WCET bounds using an instrumented hardware description of a processor 1 . Unlike traditional WCET tools, our method does not require a separate timing model or control flow reconstruction algorithm. Hence, our tool is ISA agnostic, i.e. capable of analyzing different ISAs without changes to the tool itself. Our method employs hardware/software co-analysis to analyze the program binary and processor hardware description as a single system, extending the applicability of WCET analysis to evolving processor designs. We evaluated our tool on five processors reaching a median pessimism of 27.0% and an average tool runtime of 7.81s.
- 14 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
Open AccessISA-Agnostic WCET Co-Analysis of Mixed Hardware/Software Designs
Ensuring safety-critical systems meet timing constraints is essential in aerospace, automotive, and industrial control. Failure can be catastrophic, making worst-case execution time (WCET) determination crucial. Most existing WCET tools require a pre-existing timing model for the target processor and an instruction set architecture (ISA) specific control flow reconstruction algorithm. However, in hardware/software co-design environments, where both ISA and timing behavior evolve, neither a timing model nor the control flow reconstruction algorithm may exist. We introduce a novel method for computing WCET bounds using an instrumented hardware description of a processor 1 . Unlike traditional WCET tools, our method does not require a separate timing model or control flow reconstruction algorithm. Hence, our tool is ISA agnostic, i.e. capable of analyzing different ISAs without changes to the tool itself. Our method employs hardware/software co-analysis to analyze the program binary and processor hardware description as a single system, extending the applicability of WCET analysis to evolving processor designs. We evaluated our tool on five processors reaching a median pessimism of 27.0% and an average tool runtime of 7.81s.
- Open Access
- 19 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 31 (4) , 1-24
ARDiS: A Portable and Unified Resource Management Framework in Real Hardware Systems
Designing efficient RM strategies is a cornerstone of modern computing, driving innovations in performance optimization, energy efficiency, and security. While simulators have long been the go-to tools for RM research, they fail to balance accuracy and practicality: high-fidelity simulators are excruciatingly slow, and low-fidelity ones compromise on reliability. Real hardware offers unparalleled precision and accuracy but remains underutilized due to significant barriers, including fragmented implementations, lack of portability, and prohibitive development overhead. We present ARDiS, the first open-source 1 and portable framework to provide a unified, architecture-agnostic platform for running system-level resource management (RM) techniques directly on real hardware. ARDiS eliminates the need to “reinvent the wheel,” enabling researchers to design, implement, and evaluate sophisticated RM strategies—including machine learning-based approaches—with minimal effort and maximum reproducibility. To demonstrate its versatility, we evaluate ARDiS on two real-world hardware platforms: a server-grade heterogeneous processor (Intel i9-12900) and a resource-constrained embedded system (NVIDIA Jetson TX2). Through extensive experimentation, we validate the ability of ARDiS to deliver accurate, scalable, and reproducible results across diverse platforms and application domains. By lowering the barriers to hardware-based RM research, ARDiS empowers the design automation community to explore new frontiers in system-level optimization and innovation.
- 19 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 31 (4) , 1-24
Open AccessARDiS: A Portable and Unified Resource Management Framework in Real Hardware Systems
Designing efficient RM strategies is a cornerstone of modern computing, driving innovations in performance optimization, energy efficiency, and security. While simulators have long been the go-to tools for RM research, they fail to balance accuracy and practicality: high-fidelity simulators are excruciatingly slow, and low-fidelity ones compromise on reliability. Real hardware offers unparalleled precision and accuracy but remains underutilized due to significant barriers, including fragmented implementations, lack of portability, and prohibitive development overhead. We present ARDiS, the first open-source 1 and portable framework to provide a unified, architecture-agnostic platform for running system-level resource management (RM) techniques directly on real hardware. ARDiS eliminates the need to “reinvent the wheel,” enabling researchers to design, implement, and evaluate sophisticated RM strategies—including machine learning-based approaches—with minimal effort and maximum reproducibility. To demonstrate its versatility, we evaluate ARDiS on two real-world hardware platforms: a server-grade heterogeneous processor (Intel i9-12900) and a resource-constrained embedded system (NVIDIA Jetson TX2). Through extensive experimentation, we validate the ability of ARDiS to deliver accurate, scalable, and reproducible results across diverse platforms and application domains. By lowering the barriers to hardware-based RM research, ARDiS empowers the design automation community to explore new frontiers in system-level optimization and innovation.
- Open Access
- 28 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 23-32
Special Sessions - Hardware-Software Co-Design for Machine Learning Systems Made Open-Source
- 28 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 23-32
Open AccessSpecial Sessions - Hardware-Software Co-Design for Machine Learning Systems Made Open-Source
- Open Access
Accelerated Training on Low-Power Edge Devices
Training on edge devices poses several challenges as these devices are generally resource-constrained, especially in terms of power. State-of-the-art techniques at the device level reduce the GPU frequency to enforce power constraints, leading to a significant increase in training time. To accelerate training, we propose to jointly adjust the system and application parameters (in our case, the GPU frequency and the batch size of the training task) while adhering to the power constraints on devices. We introduce a novel cross-layer methodology that combines predictions of batch size efficiency and device profiling to achieve the desired optimization. Our evaluation on real hardware shows that our method outperforms the current baselines that depend on state of the art techniques, reducing the training time by $2.4\times$ with results very close to optimal. Our measurements also indicate a substantial reduction in the overall energy used for the training process. These gains are achieved without reduction in the performance of the trained model.Open AccessAccelerated Training on Low-Power Edge Devices
Training on edge devices poses several challenges as these devices are generally resource-constrained, especially in terms of power. State-of-the-art techniques at the device level reduce the GPU frequency to enforce power constraints, leading to a significant increase in training time. To accelerate training, we propose to jointly adjust the system and application parameters (in our case, the GPU frequency and the batch size of the training task) while adhering to the power constraints on devices. We introduce a novel cross-layer methodology that combines predictions of batch size efficiency and device profiling to achieve the desired optimization. Our evaluation on real hardware shows that our method outperforms the current baselines that depend on state of the art techniques, reducing the training time by $2.4\times$ with results very close to optimal. Our measurements also indicate a substantial reduction in the overall energy used for the training process. These gains are achieved without reduction in the performance of the trained model. - 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 16 (4) , 317-320
Heterogeneous Accelerator Design for Multi-DNN Workloads via Heuristic Optimization
The significant advancements of deep neural networks (DNNs) in a wide range of application domains have spawned the need for more specialized, sophisticated solutions in the form of multi-DNN workloads. Heterogeneous DNN accelerators have emerged as an elegant solution to tackle the workloads’ inherent diversity, achieving significant improvements compared to homogeneous solutions. However, utilizing off-the-shelf architectures provides suboptimal adaptability to given workloads, whereas custom design approaches offer limited heterogeneity, and thus reduced gains. In this letter, we combat these shortcomings and propose an exploration-based framework to holistically design heterogeneous accelerators, tailored for multi-DNN workloads. Our framework is workload-agnostic and leverages architectural heterogeneity to its full potential, by integrating low-precision arithmetic and custom structural parameters. We explore the formed design space, targeting to minimize the system’s energy-delay product (EDP) via heuristic techniques. Our proposed accelerators achieve, on average, a significant $5.5\times $ reduction in EDP compared to the state of the art across various multi-DNN workloads.
- 5 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 16 (4) , 317-320
Heterogeneous Accelerator Design for Multi-DNN Workloads via Heuristic Optimization
The significant advancements of deep neural networks (DNNs) in a wide range of application domains have spawned the need for more specialized, sophisticated solutions in the form of multi-DNN workloads. Heterogeneous DNN accelerators have emerged as an elegant solution to tackle the workloads’ inherent diversity, achieving significant improvements compared to homogeneous solutions. However, utilizing off-the-shelf architectures provides suboptimal adaptability to given workloads, whereas custom design approaches offer limited heterogeneity, and thus reduced gains. In this letter, we combat these shortcomings and propose an exploration-based framework to holistically design heterogeneous accelerators, tailored for multi-DNN workloads. Our framework is workload-agnostic and leverages architectural heterogeneity to its full potential, by integrating low-precision arithmetic and custom structural parameters. We explore the formed design space, targeting to minimize the system’s energy-delay product (EDP) via heuristic techniques. Our proposed accelerators achieve, on average, a significant $5.5\times $ reduction in EDP compared to the state of the art across various multi-DNN workloads.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (11) , 3395-3406
Balancing Security and Efficiency: System-Informed Mitigation of Power-Based Covert Channels
As the digital landscape continues to evolve, the security of computing systems has become a critical concern. Power-based covert channels (e.g., thermal covert channel s (TCCs)), a form of communication that exploits the system resources to transmit information in a hidden or unintended manner, have been recently studied as an effective mechanism to leak information between malicious entities via the modulation of CPU power. To this end, dynamic voltage and frequency scaling (DVFS) has been widely used as a countermeasure to mitigate TCCs by directly affecting the communication between the actors. Although this technique has proven effective in neutralizing such attacks, it introduces significant performance and energy penalties, that are particularly detrimental to energy-constrained embedded systems. In this article, we propose different system-informed countermeasures to power-based covert channels from the heuristic and machine learning (ML) domains. Our proposed techniques leverage task migration and DVFS to jointly mitigate the channels and maximize energy efficiency. Our extensive experimental evaluation on two commercial platforms: 1) the NVIDIA Jetson TX2 and 2) Jetson Orin shows that our approach significantly improves the overall energy efficiency of the system compared to the state-of-the-art solution while nullifying the attack at all times.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (11) , 3395-3406
Balancing Security and Efficiency: System-Informed Mitigation of Power-Based Covert Channels
As the digital landscape continues to evolve, the security of computing systems has become a critical concern. Power-based covert channels (e.g., thermal covert channel s (TCCs)), a form of communication that exploits the system resources to transmit information in a hidden or unintended manner, have been recently studied as an effective mechanism to leak information between malicious entities via the modulation of CPU power. To this end, dynamic voltage and frequency scaling (DVFS) has been widely used as a countermeasure to mitigate TCCs by directly affecting the communication between the actors. Although this technique has proven effective in neutralizing such attacks, it introduces significant performance and energy penalties, that are particularly detrimental to energy-constrained embedded systems. In this article, we propose different system-informed countermeasures to power-based covert channels from the heuristic and machine learning (ML) domains. Our proposed techniques leverage task migration and DVFS to jointly mitigate the channels and maximize energy efficiency. Our extensive experimental evaluation on two commercial platforms: 1) the NVIDIA Jetson TX2 and 2) Jetson Orin shows that our approach significantly improves the overall energy efficiency of the system compared to the state-of-the-art solution while nullifying the attack at all times.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (11) , 3614-3625
ML-Based Thermal and Cache Contention Alleviation on Clustered Manycores With 3-D HBM
Enabled by the recent advancements in 2.5D/3-D integration and packaging, the integration of clustered manycore processors with high-bandwidth memory (HBM) is gaining prominence to satisfy the increasing memory bandwidth demands. Although this integration can offer significant performance gains, it is still limited by cache contention in the final-level cache on the clusters and by the thermal issues in the 3-D HBM. While the existing state-of-the-art resource management techniques have tackled these issues in isolation, we argue that the cache contention and the temperature of both the manycore and the HBM must be considered jointly to harness the full performance potential of such modern architectures. To cover this gap in the literature, we present MTCM, the first resource management technique that considers the cache contention in maximizing the system performance, while maintaining the thermal safety across both the manycore and the HBM stack. Enabled by our accurate, yet lightweight, neural network models, our proposed task migration and dynamic voltage and frequency scaling policies can accurately predict the impact of runtime decisions on the performance and temperature of both the subsystems. Our extensive evaluation experiments reveal a significant performance improvement over existing state of the art by up to $1\times $ , while maintaining thermal safety of both the manycore and the HBM.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (11) , 3614-3625
ML-Based Thermal and Cache Contention Alleviation on Clustered Manycores With 3-D HBM
Enabled by the recent advancements in 2.5D/3-D integration and packaging, the integration of clustered manycore processors with high-bandwidth memory (HBM) is gaining prominence to satisfy the increasing memory bandwidth demands. Although this integration can offer significant performance gains, it is still limited by cache contention in the final-level cache on the clusters and by the thermal issues in the 3-D HBM. While the existing state-of-the-art resource management techniques have tackled these issues in isolation, we argue that the cache contention and the temperature of both the manycore and the HBM must be considered jointly to harness the full performance potential of such modern architectures. To cover this gap in the literature, we present MTCM, the first resource management technique that considers the cache contention in maximizing the system performance, while maintaining the thermal safety across both the manycore and the HBM stack. Enabled by our accurate, yet lightweight, neural network models, our proposed task migration and dynamic voltage and frequency scaling policies can accurately predict the impact of runtime decisions on the performance and temperature of both the subsystems. Our extensive evaluation experiments reveal a significant performance improvement over existing state of the art by up to $1\times $ , while maintaining thermal safety of both the manycore and the HBM.
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 29 (1) , 1-23
NPU-Accelerated Imitation Learning for Thermal Optimization of QoS-Constrained Heterogeneous Multi-Cores
Thermal optimization of a heterogeneous clustered multi-core processor under user-defined QoS targets requires application migration and DVFS. However, selecting the core to execute each application and the VF levels of each cluster is a complex problem because (1) the diverse characteristics and QoS targets of applications require different optimizations, and (2) per-cluster DVFS requires a global optimization considering all running applications. State-of-the-art resource management for power or temperature minimization either relies on measurements that are commonly not available (such as power) or fails to consider all the dimensions of the optimization (e.g., by using simplified analytical models). To solve this, ML methods can be employed. In particular, IL leverages the optimality of an oracle policy, yet at low run-time overhead, by training a model from oracle demonstrations. We are the first to employ IL for temperature minimization under QoS targets. We tackle the complexity by training NN at design time and accelerate the run-time NN inference using NPU. While such NN accelerators are becoming increasingly widespread, they are so far only used to accelerate user applications. In contrast, we use for the first time an existing accelerator on a real platform to accelerate NN-based resource management. To show the superiority of IL compared to RL in our targeted problem, we also develop multi-agent RL-based management. Our evaluation on a HiKey 970 board with an Arm big.LITTLE CPU and NPU shows that IL achieves significant temperature reductions at a negligible run-time overhead. We compare TOP-IL against several techniques. Compared to ondemand Linux governor, TOP-IL reduces the average temperature by up to 17 ˆC at minimal QoS violations for both techniques. Compared to the RL policy, our TOP-IL achieves 63 % to 89 % fewer QoS violations while resulting similar average temperatures. Moreover, TOP-IL outperforms the RL policy in terms of stability. We additionally show that our IL-based technique also generalizes to different software (unseen applications) and even hardware (different cooling) than used for training.
- 15 November 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 29 (1) , 1-23
Open AccessNPU-Accelerated Imitation Learning for Thermal Optimization of QoS-Constrained Heterogeneous Multi-Cores
Thermal optimization of a heterogeneous clustered multi-core processor under user-defined QoS targets requires application migration and DVFS. However, selecting the core to execute each application and the VF levels of each cluster is a complex problem because (1) the diverse characteristics and QoS targets of applications require different optimizations, and (2) per-cluster DVFS requires a global optimization considering all running applications. State-of-the-art resource management for power or temperature minimization either relies on measurements that are commonly not available (such as power) or fails to consider all the dimensions of the optimization (e.g., by using simplified analytical models). To solve this, ML methods can be employed. In particular, IL leverages the optimality of an oracle policy, yet at low run-time overhead, by training a model from oracle demonstrations. We are the first to employ IL for temperature minimization under QoS targets. We tackle the complexity by training NN at design time and accelerate the run-time NN inference using NPU. While such NN accelerators are becoming increasingly widespread, they are so far only used to accelerate user applications. In contrast, we use for the first time an existing accelerator on a real platform to accelerate NN-based resource management. To show the superiority of IL compared to RL in our targeted problem, we also develop multi-agent RL-based management. Our evaluation on a HiKey 970 board with an Arm big.LITTLE CPU and NPU shows that IL achieves significant temperature reductions at a negligible run-time overhead. We compare TOP-IL against several techniques. Compared to ondemand Linux governor, TOP-IL reduces the average temperature by up to 17 ˆC at minimal QoS violations for both techniques. Compared to the RL policy, our TOP-IL achieves 63 % to 89 % fewer QoS violations while resulting similar average temperatures. Moreover, TOP-IL outperforms the RL policy in terms of stability. We additionally show that our IL-based technique also generalizes to different software (unseen applications) and even hardware (different cooling) than used for training.