Peter Wägemann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Peter Wägemann has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Luis Gerhorst
Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
4 shared publications - Rüdiger Kapitza
Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
4 shared publications Phillip Raffeck
Department of Computer Science, Distributed Systems and Operating Systems, Friedrich-Alexander University Erlangen-NC<rnberg (FAU)
3 shared publications- Phillip Raffeck
Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
3 shared publications Wolfgang Schroder-Preikschat
3 shared publications- Wolfgang Schröder-Preikschat
Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
3 shared publications
Latest Publications
- 29 October 2026
- Published by Springer Nature
- p. 192-220
Firefly: High-Performance Transient Execution Attack Defenses for In-Kernel Sandboxes
- 29 October 2026
- Published by Springer Nature
- p. 192-220
Firefly: High-Performance Transient Execution Attack Defenses for In-Kernel Sandboxes
- Open Access
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 68-76
z B ulk : Towards Automatic Compartmentalization in Rust with Zero Manual Retrofitting
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 68-76
Open Accessz B ulk : Towards Automatic Compartmentalization in Rust with Zero Manual Retrofitting
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 97-108
vNV-Heap: An Ownership-Based Virtually Non-Volatile Heap for Embedded Systems
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 97-108
Open AccessvNV-Heap: An Ownership-Based Virtually Non-Volatile Heap for Embedded Systems
- Open Access
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Reverse Engineering the ESP32-C3 Wi-Fi Drivers for Static Worst-Case Analysis of Intermittently-Powered Systems
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessReverse Engineering the ESP32-C3 Wi-Fi Drivers for Static Worst-Case Analysis of Intermittently-Powered Systems
- Open Access
- 18 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 193747-193762
TinyEP: TinyML-Enhanced Energy Profiling for Extreme Edge Devices
The widespread integration of the Internet of Things (IoT) into daily operations has made optimizing energy consumption in low-power edge devices increasingly important. This is especially critical when battery-powered IoT platforms, like sensor networks, are provided to third parties to run custom sensing and perception applications. In such cases, two main requirements emerge: (A) accurate measurement of task energy consumption to fairly distribute maintenance and operations costs among parties and (B) reliable identification of tasks with high power consumption fluctuations to prevent interference with sensitive measurement campaigns. However, the need for compact, cost-effective, and energy-efficient power measurement solutions often compromises dynamic range, resolution, and overall measurement quality in these platforms. To address these challenges, we introduce TinyEP, a system that leverages machine learning on highly constrained microcontrollers (TinyML) to enhance the quality of power traces recorded by limited measurement hardware on highly constrained devices in real-time. Our approach incorporates online learning in the final layer of the model, combined with sparse feedback from an existing battery fuel gauge IC, to automatically adapt to new environments and compensate for concept drift. We evaluated the robustness of TinyEP under extreme conditions, demonstrating its effective operation within a temperature range of –40 °C to 80 °C. Our results show that TinyEP improves the Mean Absolute Percentage Error (MAPE) in recorded power traces and reduces the MAPE in task energy measurements from over 2% to under 0.8% across all tested scenarios. Additionally, it significantly decreases residual variance during task energy measurements.
- 18 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 193747-193762
Open AccessTinyEP: TinyML-Enhanced Energy Profiling for Extreme Edge Devices
The widespread integration of the Internet of Things (IoT) into daily operations has made optimizing energy consumption in low-power edge devices increasingly important. This is especially critical when battery-powered IoT platforms, like sensor networks, are provided to third parties to run custom sensing and perception applications. In such cases, two main requirements emerge: (A) accurate measurement of task energy consumption to fairly distribute maintenance and operations costs among parties and (B) reliable identification of tasks with high power consumption fluctuations to prevent interference with sensitive measurement campaigns. However, the need for compact, cost-effective, and energy-efficient power measurement solutions often compromises dynamic range, resolution, and overall measurement quality in these platforms. To address these challenges, we introduce TinyEP, a system that leverages machine learning on highly constrained microcontrollers (TinyML) to enhance the quality of power traces recorded by limited measurement hardware on highly constrained devices in real-time. Our approach incorporates online learning in the final layer of the model, combined with sparse feedback from an existing battery fuel gauge IC, to automatically adapt to new environments and compensate for concept drift. We evaluated the robustness of TinyEP under extreme conditions, demonstrating its effective operation within a temperature range of –40 °C to 80 °C. Our results show that TinyEP improves the Mean Absolute Percentage Error (MAPE) in recorded power traces and reduces the MAPE in task energy measurements from over 2% to under 0.8% across all tested scenarios. Additionally, it significantly decreases residual variance during task energy measurements.
- Open Access
- 30 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 644-659
VeriFence: Lightweight and Precise Spectre Defenses for Untrusted Linux Kernel Extensions
High-performance IO demands low-overhead communication between user- and kernel space. This demand can no longer be fulfilled by traditional system calls. Linux’s extended Berkeley Packet Filter (BPF) avoids user-/kernel transitions by just-in-time compiling user-provided bytecode and executing it in kernel mode with near-native speed. To still isolate BPF programs from the kernel, they are statically analyzed for memory- and type-safety, which imposes some restrictions but allows for good expressiveness and high performance. However, to mitigate the Spectre vulnerabilities disclosed in 2018, defenses which reject potentially-dangerous programs had to be deployed. We find that this affects Math 1 to Math 2 of programs in a dataset with 844 real-world BPF programs from popular open-source projects. To solve this, users are forced to disable the defenses to continue using the programs, which puts the entire system at risk. To enable secure and expressive untrusted Linux kernel extensions, we propose VeriFence, an enhancement to the kernel’s Spectre defenses that reduces the number of BPF application programs rejected from Math 3 to zero. We measure VeriFence’s overhead for all mainstream performance-sensitive applications of BPF (i.e., event tracing, profiling, and packet processing) and find that it improves significantly upon the status-quo where affected BPF programs are either unusable or enable transient execution attacks on the kernel.
- 30 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 644-659
Open AccessVeriFence: Lightweight and Precise Spectre Defenses for Untrusted Linux Kernel Extensions
High-performance IO demands low-overhead communication between user- and kernel space. This demand can no longer be fulfilled by traditional system calls. Linux’s extended Berkeley Packet Filter (BPF) avoids user-/kernel transitions by just-in-time compiling user-provided bytecode and executing it in kernel mode with near-native speed. To still isolate BPF programs from the kernel, they are statically analyzed for memory- and type-safety, which imposes some restrictions but allows for good expressiveness and high performance. However, to mitigate the Spectre vulnerabilities disclosed in 2018, defenses which reject potentially-dangerous programs had to be deployed. We find that this affects Math 1 to Math 2 of programs in a dataset with 844 real-world BPF programs from popular open-source projects. To solve this, users are forced to disable the defenses to continue using the programs, which puts the entire system at risk. To enable secure and expressive untrusted Linux kernel extensions, we propose VeriFence, an enhancement to the kernel’s Spectre defenses that reduces the number of BPF application programs rejected from Math 3 to zero. We measure VeriFence’s overhead for all mainstream performance-sensitive applications of BPF (i.e., event tracing, profiling, and packet processing) and find that it improves significantly upon the status-quo where affected BPF programs are either unusable or enable transient execution attacks on the kernel.
- Open Access
- 20 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 83-94
WoCA: Avoiding Intermittent Execution in Embedded Systems by Worst-Case Analyses with Device States
Embedded systems with intermittent energy supply can revolutionize the Internet of Things, as they are energy self-sufficient due to energy harvesting. Existing intermittent-computing approaches, running directly from non-volatile memory, allow incremental progress of machine-code instructions. However, this progress does not apply to many devices (e.g., transceivers) having transactional (i.e., all-or-nothing) semantics: Power failures during transactions lead to starvation when frequently experiencing failed attempts. We introduce WoCA, an approach that exploits static, whole-system worst-case analysis for device-driven intermittent computing. With the currently available energy, WoCA enables transactional device uses and guarantees forward progress. WoCA's novel static analysis tracks program-path-sensitive device states and transitions to yield energy bounds. With these bounds, WoCA's runtime decides when to safely execute code between checkpoints. Using WoCA's hardware platform, we validate that WoCA makes more efficient use of available energy compared to worst-case-agnostic approaches, while also giving runtime guarantees.
- 20 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 83-94
Open AccessWoCA: Avoiding Intermittent Execution in Embedded Systems by Worst-Case Analyses with Device States
Embedded systems with intermittent energy supply can revolutionize the Internet of Things, as they are energy self-sufficient due to energy harvesting. Existing intermittent-computing approaches, running directly from non-volatile memory, allow incremental progress of machine-code instructions. However, this progress does not apply to many devices (e.g., transceivers) having transactional (i.e., all-or-nothing) semantics: Power failures during transactions lead to starvation when frequently experiencing failed attempts. We introduce WoCA, an approach that exploits static, whole-system worst-case analysis for device-driven intermittent computing. With the currently available energy, WoCA enables transactional device uses and guarantees forward progress. WoCA's novel static analysis tracks program-path-sensitive device states and transitions to yield energy bounds. With these bounds, WoCA's runtime decides when to safely execute code between checkpoints. Using WoCA's hardware platform, we validate that WoCA makes more efficient use of available energy compared to worst-case-agnostic approaches, while also giving runtime guarantees.
- Open Access
- 2 April 2020
- Published by Public Library of Science (PLoS) in PLOS Biology
- Vol. 18 (4) , e3000655
Thinking small: Next-generation sensor networks close the size gap in vertebrate biologging
Recent advances in animal tracking technology have ushered in a new era in biologging. However, the considerable size of many sophisticated biologging devices restricts their application to larger animals, whereas older techniques often still represent the state-of-the-art for studying small vertebrates. In industrial applications, low-power wireless sensor networks (WSNs) fulfill requirements similar to those needed to monitor animal behavior at high resolution and at low tag mass. We developed a wireless biologging network (WBN), which enables simultaneous direct proximity sensing, high-resolution tracking, and long-range remote data download at tag masses of 1 to 2 g. Deployments to study wild bats created social networks and flight trajectories of unprecedented quality. Our developments highlight the vast capabilities of WBNs and their potential to close an important gap in biologging: fully automated tracking and proximity sensing of small animals, even in closed habitats, at high spatial and temporal resolution.
- 2 April 2020
- Published by Public Library of Science (PLoS) in PLOS Biology
- Vol. 18 (4) , e3000655
Open AccessThinking small: Next-generation sensor networks close the size gap in vertebrate biologging
Recent advances in animal tracking technology have ushered in a new era in biologging. However, the considerable size of many sophisticated biologging devices restricts their application to larger animals, whereas older techniques often still represent the state-of-the-art for studying small vertebrates. In industrial applications, low-power wireless sensor networks (WSNs) fulfill requirements similar to those needed to monitor animal behavior at high resolution and at low tag mass. We developed a wireless biologging network (WBN), which enables simultaneous direct proximity sensing, high-resolution tracking, and long-range remote data download at tag masses of 1 to 2 g. Deployments to study wild bats created social networks and flight trajectories of unprecedented quality. Our developments highlight the vast capabilities of WBNs and their potential to close an important gap in biologging: fully automated tracking and proximity sensing of small animals, even in closed habitats, at high spatial and temporal resolution.
- Open Access
BATS: Adaptive Ultra Low Power Sensor Network for Animal Tracking
In this paper, the BATS project is presented, which aims to track the behavior of bats via an ultra-low power wireless sensor network. An overview about the whole project and its parts like sensor node design, tracking grid and software infrastructure is given and the evaluation of the project is shown. The BATS project includes a lightweight sensor node that is attached to bats and combines multiple features. Communication among sensor nodes allows tracking of bat encounters. Flight trajectories of individual tagged bats can be recorded at high spatial and temporal resolution by a ground node grid. To increase the communication range, the BATS project implemented a long-range telemetry system to still receive sensor data outside the standard ground node network. The whole system is designed with the common goal of ultra-low energy consumption while still maintaining optimal measurement results. To this end, the system is designed in a flexible way and is able to adapt its functionality according to the current situation. In this way, it uses the energy available on the sensor node as efficient as possible.
Open AccessBATS: Adaptive Ultra Low Power Sensor Network for Animal Tracking
In this paper, the BATS project is presented, which aims to track the behavior of bats via an ultra-low power wireless sensor network. An overview about the whole project and its parts like sensor node design, tracking grid and software infrastructure is given and the evaluation of the project is shown. The BATS project includes a lightweight sensor node that is attached to bats and combines multiple features. Communication among sensor nodes allows tracking of bat encounters. Flight trajectories of individual tagged bats can be recorded at high spatial and temporal resolution by a ground node grid. To increase the communication range, the BATS project implemented a long-range telemetry system to still receive sensor data outside the standard ground node network. The whole system is designed with the common goal of ultra-low energy consumption while still maintaining optimal measurement results. To this end, the system is designed in a flexible way and is able to adapt its functionality according to the current situation. In this way, it uses the energy available on the sensor node as efficient as possible.
- 4 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 11 (2) , 38-41
Combining Automated Measurement-Based Cost Modeling With Static Worst-Case Execution-Time and Energy-Consumption Analyses
Predicting the temporal behavior of embedded real-time systems is a crucial but challenging task, as it is with the energetic behavior of energy-constrained systems, such as IoT devices. To carry out static analyses in order to determine the worst-case execution time (WCET) or the worst-case energy consumption (WCEC) of tasks, cost models are inevitable. However, these models are rarely available on a fine-grained level for commercial-off-the-shelf hardware platforms. In this paper, we present NEO, an end-to-end toolchain that automatically generates cost models, which are then integrated into an existing static-analysis tool. NEO exploits automatically generated benchmark programs, which are measured on the target platform and investigated in a virtual machine. Based on the gathered data, we formulate mathematical optimization problems that eventually yield both worst-case execution-time and energy-consumption cost models. In our evaluations with an embedded hardware platform (e.g., ARM Cortex-M0+), we show that the open-source toolchain is able to precisely bound programs’ resources while achieving acceptable accuracy.
- 4 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 11 (2) , 38-41
Combining Automated Measurement-Based Cost Modeling With Static Worst-Case Execution-Time and Energy-Consumption Analyses
Predicting the temporal behavior of embedded real-time systems is a crucial but challenging task, as it is with the energetic behavior of energy-constrained systems, such as IoT devices. To carry out static analyses in order to determine the worst-case execution time (WCET) or the worst-case energy consumption (WCEC) of tasks, cost models are inevitable. However, these models are rarely available on a fine-grained level for commercial-off-the-shelf hardware platforms. In this paper, we present NEO, an end-to-end toolchain that automatically generates cost models, which are then integrated into an existing static-analysis tool. NEO exploits automatically generated benchmark programs, which are measured on the target platform and investigated in a virtual machine. Based on the gathered data, we formulate mathematical optimization problems that eventually yield both worst-case execution-time and energy-consumption cost models. In our evaluations with an embedded hardware platform (e.g., ARM Cortex-M0+), we show that the open-source toolchain is able to precisely bound programs’ resources while achieving acceptable accuracy.