Tobias Kilian
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tobias Kilian has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Ulf Schlichtmann
Technical University of Munich, Munich, Bavaria, Germany
5 shared publications - Martin Huch
Infineon Technologies AG, Neubiberg, Germany
4 shared publications - Giovanni Squillero
Politecnico di Torino, Torino, Italy
3 shared publications - Nicolò Bellarmino
Politecnico di Torino, Turin, Italy
3 shared publications - Riccardo Cantoro
DAUIN, Politecnico di Torino, Turin, Italy
3 shared publications Daniel Tille
Infineon Technologies AG, Munich, Germany
2 shared publications
Latest Publications
- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (2) , 652-664
COSMO: COmpressed Sensing for Models and Logging Optimization in MCU Performance Screening
In safety-critical applications, microcontrollers must meet stringent quality and performance standards, including the maximum operating frequency$F_{\max}$ . Machine learning models have proven effective in estimating$F_{\max}$ by utilizing data from on-chip ring oscillators. Previous research has shown that increasing the number of ring oscillators on board can enable the deployment of simple linear regression models to predict$F_{\max}$ . However, the scarcity of labeled data that characterize this context poses a challenge in managing high-dimensional feature spaces; moreover, a very high number of ring oscillators is not desirable due to technological reasons. By modeling$F_{\max}$ as a linear combination of the ring oscillators’ values, this paper employs Compressed Sensing theory to build the model and perform feature selection, enhancing model efficiency and interpretability. We explore regularized linear methods with convex/non-convex penalties in microcontroller performance screening, focusing on selecting informative ring oscillators. This permits reducing models’ footprint while retaining high prediction accuracy. Our experiments on two real-world microcontroller products compare Compressed Sensing with two alternative feature selection approaches: filter and wrapped methods. In our experiments, regularized linear models effectively identify relevant ring oscillators, achieving compression rates of up to 32:1, with no substantial loss in prediction metrics.- 20 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (2) , 652-664
COSMO: COmpressed Sensing for Models and Logging Optimization in MCU Performance Screening
In safety-critical applications, microcontrollers must meet stringent quality and performance standards, including the maximum operating frequency$F_{\max}$ . Machine learning models have proven effective in estimating$F_{\max}$ by utilizing data from on-chip ring oscillators. Previous research has shown that increasing the number of ring oscillators on board can enable the deployment of simple linear regression models to predict$F_{\max}$ . However, the scarcity of labeled data that characterize this context poses a challenge in managing high-dimensional feature spaces; moreover, a very high number of ring oscillators is not desirable due to technological reasons. By modeling$F_{\max}$ as a linear combination of the ring oscillators’ values, this paper employs Compressed Sensing theory to build the model and perform feature selection, enhancing model efficiency and interpretability. We explore regularized linear methods with convex/non-convex penalties in microcontroller performance screening, focusing on selecting informative ring oscillators. This permits reducing models’ footprint while retaining high prediction accuracy. Our experiments on two real-world microcontroller products compare Compressed Sensing with two alternative feature selection approaches: filter and wrapped methods. In our experiments, regularized linear models effectively identify relevant ring oscillators, achieving compression rates of up to 32:1, with no substantial loss in prediction metrics.- 1 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44 (2) , 641-654
Deep Learning Strategies for Labeling and Accuracy Optimization in Microcontroller Performance Screening
In safety-critical applications, microcontrollers must be compliant with the required quality constraints and performance standards, particularly in terms of the maximum operating frequency $(F_{\max })$ . Machine learning (ML) models have proven effective in estimating $F_{\max }$ by utilizing data extracted from on-chip ring oscillators (ROs), making them a valuable instrument for performance screening. However, the cost of obtaining labeled samples and the stringent accuracy needed by the model create hard challenges in this context. In order to address these, we explored three deep-learning (DL)-based key strategies: 1) semi-supervised learning with deep feature extractors: we leverage the abundance of unlabeled production data in a semi-supervised approach. Deep feature extractor models are employed to transform data into higher-dimensional spaces. These feature embeddings enable accurate performance prediction using simple linear regression, with a fraction of labeled data to reach baseline performances; 2) intrafamily transfer learning: when introducing new microcontroller products, with slightly different characteristics but the same set of ROs, previously trained deep feature extractors can be used, in a transfer learning fashion. This permits the use of significantly fewer labeled data compared to traditional methods; and 3) interfamily transfer learning: we extend the previous transfer learning concept to new microcontroller products with completely distinct characteristics. We aim to demonstrate that adapting the features set and fine-tuning DL feature extractors initially trained on specific legacy product data permits to yield better performance. Our research aims to provide a holistic framework for DL-based microcontroller performance screening to address the challenge of limited labeled data. The proposed methodologies significantly improve prediction accuracy and reduce the dependency on a large number of labeled samples, thus enhancing the efficiency and efficacy of ML-based microcontroller screening. The proposed framework enables models reuse, serving as a valuable baseline when new products are released.
- 1 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44 (2) , 641-654
Deep Learning Strategies for Labeling and Accuracy Optimization in Microcontroller Performance Screening
In safety-critical applications, microcontrollers must be compliant with the required quality constraints and performance standards, particularly in terms of the maximum operating frequency $(F_{\max })$ . Machine learning (ML) models have proven effective in estimating $F_{\max }$ by utilizing data extracted from on-chip ring oscillators (ROs), making them a valuable instrument for performance screening. However, the cost of obtaining labeled samples and the stringent accuracy needed by the model create hard challenges in this context. In order to address these, we explored three deep-learning (DL)-based key strategies: 1) semi-supervised learning with deep feature extractors: we leverage the abundance of unlabeled production data in a semi-supervised approach. Deep feature extractor models are employed to transform data into higher-dimensional spaces. These feature embeddings enable accurate performance prediction using simple linear regression, with a fraction of labeled data to reach baseline performances; 2) intrafamily transfer learning: when introducing new microcontroller products, with slightly different characteristics but the same set of ROs, previously trained deep feature extractors can be used, in a transfer learning fashion. This permits the use of significantly fewer labeled data compared to traditional methods; and 3) interfamily transfer learning: we extend the previous transfer learning concept to new microcontroller products with completely distinct characteristics. We aim to demonstrate that adapting the features set and fine-tuning DL feature extractors initially trained on specific legacy product data permits to yield better performance. Our research aims to provide a holistic framework for DL-based microcontroller performance screening to address the challenge of limited labeled data. The proposed methodologies significantly improve prediction accuracy and reduce the dependency on a large number of labeled samples, thus enhancing the efficiency and efficacy of ML-based microcontroller screening. The proposed framework enables models reuse, serving as a valuable baseline when new products are released.
- 10 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Design & Test
- Vol. 41 (6) , 46-53
On the Relation Between Reliability and Entropy in Physical Unclonable Functions
Physical Unclonable Functions (PUFs) are integral for generating unique signatures, secret keys, and device identification, leveraging inherent manufacturing process variability. Mathematically defined as functions linking inputs (challenges) to outputs (responses), PUFs exhibit random properties. Key properties for high-quality PUFs include intra-device entropy (random distribution of responses within the same circuit), inter-device entropy (random distribution across different circuits for identical challenges), and reliability (response consistency for identical challenges and the same circuit). Inter-device entropy and reliability may be influenced by design discrepancies, systematic variability, noise, and aging. This paper addresses the correlation between entropy and reliability, providing evidence from an extensive set of circuits featuring diverse Ring Oscillators supplied by Infineon.
- 10 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Design & Test
- Vol. 41 (6) , 46-53
On the Relation Between Reliability and Entropy in Physical Unclonable Functions
Physical Unclonable Functions (PUFs) are integral for generating unique signatures, secret keys, and device identification, leveraging inherent manufacturing process variability. Mathematically defined as functions linking inputs (challenges) to outputs (responses), PUFs exhibit random properties. Key properties for high-quality PUFs include intra-device entropy (random distribution of responses within the same circuit), inter-device entropy (random distribution across different circuits for identical challenges), and reliability (response consistency for identical challenges and the same circuit). Inter-device entropy and reliability may be influenced by design discrepancies, systematic variability, noise, and aging. This paper addresses the correlation between entropy and reliability, providing evidence from an extensive set of circuits featuring diverse Ring Oscillators supplied by Infineon.
- 13 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 31 (6) , 711-724
Performance Screening Using Functional Path Ring Oscillators
The testing of integrated circuits is an important topic, particularly in safety-critical applications. This is especially true for microcontrollers (MCUs) used in the automotive industry. A critical test is the performance screening in which the maximum clock frequency of the MCU is determined. For this performance screening, indirect monitors, such as ring oscillators (ROs), are used. This article presents a holistic overview of the functional path RO from the pre-silicon to the post-silicon. The implementation of such ROs is presented, as the associated advantages in terms of area consumption, leakage, and routing. In the post-silicon phase, the functional path RO frequencies are correlated with the MCU performance using machine learning approaches.
- 13 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 31 (6) , 711-724
Performance Screening Using Functional Path Ring Oscillators
The testing of integrated circuits is an important topic, particularly in safety-critical applications. This is especially true for microcontrollers (MCUs) used in the automotive industry. A critical test is the performance screening in which the maximum clock frequency of the MCU is determined. For this performance screening, indirect monitors, such as ring oscillators (ROs), are used. This article presents a holistic overview of the functional path RO from the pre-silicon to the post-silicon. The implementation of such ROs is presented, as the associated advantages in terms of area consumption, leakage, and routing. In the post-silicon phase, the functional path RO frequencies are correlated with the MCU performance using machine learning approaches.
- 16 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 42 (10) , 3436-3449
A Multilabel Active Learning Framework for Microcontroller Performance Screening
In safety-critical applications, microcontrollers have to be tested to satisfy strict quality and performance constraints. It has been demonstrated that on-chip ring oscillators can be used as speed monitors to reliably predict the performances. However, any machine-learning (ML) model is likely to be inaccurate if trained on an inadequate dataset, and labeling data for training is quite a costly process. In this article, we present a methodology based on active learning to select the best samples to be included in the training set, significantly reducing the time and cost required. Moreover, since different speed measurements are available, we designed a multilabel technique to take advantage of their correlations. Experimental results demonstrate that the approach halves the training-set size, with respect to a random-labeling, while it increases the predictive accuracy, with respect to standard single-label ML models.
- 16 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 42 (10) , 3436-3449
A Multilabel Active Learning Framework for Microcontroller Performance Screening
In safety-critical applications, microcontrollers have to be tested to satisfy strict quality and performance constraints. It has been demonstrated that on-chip ring oscillators can be used as speed monitors to reliably predict the performances. However, any machine-learning (ML) model is likely to be inaccurate if trained on an inadequate dataset, and labeling data for training is quite a costly process. In this article, we present a methodology based on active learning to select the best samples to be included in the training set, significantly reducing the time and cost required. Moreover, since different speed measurements are available, we designed a multilabel technique to take advantage of their correlations. Experimental results demonstrate that the approach halves the training-set size, with respect to a random-labeling, while it increases the predictive accuracy, with respect to standard single-label ML models.