Pasar al contenido principal

Encapsulación de soluciones basadas en IA para acelerar su adopción

PLEC2023-010240

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i en Líneas Estratégicas
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario BARCELONA SUPERCOMPUTING CENTER CENTRO NACIONAL DE SUPERCOMPUTACION

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Exploring the limits of software-only diverse redundancy on an Intel GPU

  • Andriotis, Nikolaos
  • Serrano-Cases, Alejandro
  • Alcaide, Sergi
  • Cazorla, Francisco J.
  • Abella, Jaume
  • Serrano-Cases, Alejandro|||/items/09bc6bdc-e4fd-4043-835a-48fee62ed569
The advent of Autonomous Driving (AD) in the automotive domain, and AD’s high dependence on compute-intensive Artificial Intelligence (AI) based tasks makes the use of graphics processing units (GPUs) mandatory in those systems. However, AD controls systems with the most stringent safety integrity levels like steering and braking that impose the use of diverse redundancy in accordance with ISO 26262 functional safety standard for road vehicles. Since commercial GPUs lack explicit support for diverse redundancy, software-only solutions making redundant tasks use disjoint sets of computing resources should be explored. So far, some solutions have been proposed to achieve high (yet not full) degrees of diversity on NVIDIA GPUs, as well as full diversity (for the computing resources) on Intel GPUs subject to meeting two constraints: (1) being able to split the work into a fixed number of software threads matching the number of hardware threads, and (2) having a hardware scheduler allocating all hardware threads in a perfect round-robin fashion. The first constraint cannot be easily met and may harm performance due to work imbalance, whereas the second is fully dependent on the GPU implementation, and can only be assessed empirically to some extent. This paper provides a new solution to achieve diverse redundancy for the computing resources in COTS GPUs, proven on an Intel X GPU, overcoming the limitations of existing solutions. In particular, our approach avoids constraints on the number of software threads used and the hardware scheduler allocation policies. Our approach builds on a first phase making each software thread select the piece of work to carry out based on the hardware thread where it has been scheduled with no need for synchronization, and a second phase in which the limitations of the hardware scheduling policy are managed securing workload execution while sacrificing very little diversity. We realize our approach in a last generation Intel GPU for which we show low performance overheads, but the very same strategy can be ported to other GPU families (e.g., NVIDIA, and Arm).
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Semantic diverse redundancy for robust multi-modal safety-critical AI tasks

  • Caro Roca, Martí
  • Brando Guillaumes, Axel
  • Abella Ferrer, Jaume|||0000-0001-7951-4028
Dual Modular Redundancy (DMR) and Triple Modular Redundancy (TMR), often combined with diversity techniques, are widely used in safety-critical systems to achieve fault detection and/or tolerance. Traditional redundancy expects bit-identical outputs, flagging any mismatch as an error. However, emerging AI-based functionalities, such as camera and LiDAR-based object detection, are intrinsically stochastic and require only semantic correctness, allowing some variation in the outputs (e.g., slightly different confidence scores). In this work, we extend our previous semantic redundancy approach – originally developed for camera-based object detection – to LiDAR-based systems, which operate on 3D point cloud data. We propose software-only DMR and TMR schemes that introduce data-level diversity through domain-specific input transformations, preserving semantic meaning while increasing robustness. Our findings demonstrate that the method can be generalized to different AI tasks, helping improve safety and reliability in the different AI components of safety-critical systems., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num. 101069595. This work is also part of the project PLEC2023- 010240 funded by MICIU/AEI/10.13039/501100011033. M. Caro has received funding under grant PRE2022-102440 funded by MICIU/AEI/10.13039/501100011033 and, by ESF+., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Supporting timing-related metrics for autonomous driving frameworks in CyberRT

  • Alcón Doganoc, Miguel
  • Mezzetti, Enrico|||0000-0002-1886-2931
  • Abella Ferrer, Jaume|||0000-0001-7951-4028
  • Cazorla Almeida, Francisco Javier
The provision of increasingly advanced autonomous software functionalities builds on cutting-edge autonomous driving frameworks to enable modular interactions among multiple software components. This approach helps to support functional cause-effect chains from multiple sensors to actuators. The complexity of the (software) component interactions makes it more difficult to ascertain the correctness of the timing behavior of the system. This is so because traditional timing-related metrics like worst-case execution and worst-case response time do not capture the inter-dependency in cause-effect chains between the input sampling time and the time at which computation based on those inputs is performed. Complementary timing-related metrics, such as maximum reaction time and maximum data age have been considered to capture timing requirements, typically with an end-to-end scope, in cause-effect chains. These metrics have been formalized and demonstrated in ROS2-based automotive and autonomous driving setups. However, the formalization of those metrics, which is necessary for deriving analytical lower and upper bounds and monitoring them at run-time, largely depends on the execution model and semantics offered by the run-time. Any concrete application of those metrics need to be tailored and adapted to the system at hand. Apollo auto is a popular, industrial-quality, open-source autonomous driving framework that is seeing increasing adoption both for industrial and academic projects. Apollo builds on CyberRT, an ad-hoc run-time that is similar in mechanism and intent to ROS2 but differentiates from it with respect to execution model and supported semantics. In contrast to ROS2, CyberRT is highly specialized to support the Apollo AD framework, is neither extensively documented or thoroughly analysed in the literature, especially in relation to execution model and instantiation of timing-related metrics. In this work, for the first time, we provide an insightful analysis and discussion on CyberRT execution model and semantics, starting from its raw and non-extensively documented codebase. Based on the identified semantics, we elaborate a formalization of timing-related metrics on CyberRT, across different granularity scopes, namely end-to-end and node levels. In particular, we develop on the importance of node-level timing properties to intercept any latent timing misbehavior before it is too late, and it severely impacts end-to-end execution. We provide a concrete mapping of a comprehensive set of timing-related metrics to the CyberRT execution model, both at end-to-end and node level, and develop a monitoring library that allows to intercept them on the specific software stack. We exploit the proposed library on a set of Apollo autonomous driving scenarios to demonstrate its effectiveness in monitoring the considered timing metrics and to promptly intercept a subtle timing misbehavior beyond end-to-end execution scope in a representative autonomous driving stack., T his work has been supported by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101139892 (EdgeAI-Trust); by the project PLEC2023-010240, funded by MICIU/AEI /10.13039/501100011033 (CAPSUL-IA);andbytheMiguelAlcónfellowshipwithinthe”GeneraciónD”initiative,Red.es,Ministerio parala Transformación Digital ydelaFunciónPública,fortalentattraction(C005/24-EDCV1),fundedbytheEuropeanUnionNextGenerationEU funds through PRTR., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Event monitor validation in high-integrity systems

  • Pujol Torramorell, Roger
  • Vilardell Moreno, Sergi
  • Mezzetti, Enrico|||0000-0002-1886-2931
  • Hassan, Mohamed
  • Abella Ferrer, Jaume|||0000-0001-7951-4028
  • Cazorla Almeida, Francisco Javier
Platforms for modern embedded systems equip an increasing number of high-performance features to provide the required levels of performance. Timing analysis solutions handle the complexity of these platforms by relying on hardware event monitors (HEMs) that provide insightful information about resource utilization and, hence, contention among tasks. As a result, HEMs have become a key element to warrant a safe timing behavior of a system, for which reason they must be validated. While some initial works target HEMs validation, they consider one HEM at a time and focus on those HEMs for which an expert can establish an expected value for relatively small code snippets. In this paper, we propose a methodology for the validation of those HEMs for which a specific expected value cannot be established a priori even for simple cases and, instead, needs to be validated in conjunction with other HEMs. Our method also deals with the natural variability of the HEMs' values in high-performance platforms when collected in different experiments. We illustrate the effectiveness of our proposed technique for validating HEMs related to cache coherence in a relevant platform in the avionics domain., This work has been supported by project PLEC2023-010240 funded by MICIU/AEI/10.13039/501100011033, the European Union’s Horizon Europe research and innovation programme under grant agreement No. 101070238, and the Natural Sciences and Engineering Research Council of Canada (NSERC). The authors also thank the support of the Department of Research and Universities of the Government of Catalonia to the Smart and Safe Autonomous Systems (SSAS) Research Group, (Code: 2021 SGR 00637)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Safety-relevant AI-based system robustification with neural network ensembles

  • Aldomà Coll, Adrià|||0009-0005-1270-0295
  • Brando Guillaumes, Axel
  • Cazorla Almeida, Francisco Javier
  • Abella Ferrer, Jaume|||0000-0001-7951-4028
Functional safety requirements of AI-based safety-critical applications challenge AI models, whose accuracy can be limited. In this paper, we show how using several cooperative deep learning (DL) models helps to raise global accuracy and reject making a prediction when confidence is below a pre-established threshold., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num. 101069595. This work has also been supported by the Project PLEC2023-010240 funded by MICIU/AEI/10.13039/501100011033. Authors thank the support given to the Research Group SSAS (Code: 2021 SGR 00637) by the Research and University Department of the Generalitat de Catalunya., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Leveraging image-based transformations to mitigate adversarial attacks in AI-based safety-critical systems

  • Caro Roca, Martí
  • Brando Guillaumes, Axel
  • Abella Ferrer, Jaume|||0000-0001-7951-4028
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. https://dx.doi.org/10.1109/IOLTS65288.2025.11116992, Dual (DMR) and Triple Modular Redundancy (TMR) are widely used techniques to provide fault detection and/or tolerance capabilities in safety-critical systems through – often diverse – redundancy. However, these systems remain vulnerable to adversarial attacks, which can mislead the AI models and lead to severe consequences. In this paper, we propose enhanced DMR and TMR implementations for image-based object detection leveraging image transformations during inference to mitigate the impact of adversarial attacks, hence addressing safety and security concerns simultaneously. Our approach achieves up to 12.9% and 12.2% higher accuracy in adversarial scenarios compared to state-of-the-art solutions in DMR and TMR configurations, respectively., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num.101069595. This work is also part of the project PLEC2023-010240 funded by ICIU/AEI/10.13039/501100011033. M. Caro has received funding under grant PRE2022-102440 funded by MICIU/AEI/10.13039/501100011033 and, by ESF+., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Detecting low-density mixtures in high-quantile tails for pWCET estimation

  • Manau Corderroure, Blau
  • Vilardell Moreno, Sergi
  • Serra Mochales, Isabel
  • Mezzetti, Enrico|||0000-0002-1886-2931
  • Abella Ferrer, Jaume|||0000-0001-7951-4028
  • Cazorla Almeida, Francisco Javier
The variability arising from sophisticated hardware and software solutions in cutting-edge embedded products causes software to exhibit complex execution time distributions. Mixture distributions can happen, with different density (weight), as a result of inherent different features in the execution platform and multiple operational scenarios. In the context of probabilistic WCET (pWCET) analysis based on Extreme Value Theory (EVT), where identical distribution is a pre-requisite, mixtures are typically intercepted by applying stationarity tests on the full sample. Those tests, however, are instructed to detect only mixtures with sufficiently high probability (weight) and disregard low-density mixtures (which are unlikely to be preserved in the high-quantile tail of the sample) as they would prevent any form of stationarity. Nonetheless, low-density mixture distributions can persist and even exacerbate in the tail, and, when not considered, they can impair pWCET estimation in EVT-based approaches, leading to overly pessimistic or optimistic bounds. In this work, we propose TailID, an iterative point-wise approach that builds on the asymptotic convergence of the Maximum Likelihood Estimator (MLE) of the Extreme Value Index (EVI) parameter ξ to detect low-density mixture distributions on high-quantile tails and use this information to steer EVT tail selection. The benefits of the proposed method are assessed on synthetic mixture distributions and real data collected on an industrially representative embedded platform., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num. 101069595 and project PLEC2023-010240 funded by MICIU/AEI/10.13039/501100011033 (CAPSUL-IA). Authors also appreciate the support given to the Research Group SSAS (Code: 2021 SGR 00637) by the Research and University Department of the Generalitat de Catalunya. This work is partially supported by the Spanish MICIU with project PID2022-137414OB-I00., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Supporting timing-related metrics for autonomous driving frameworks in CyberRT

  • Alcón Doganoc, Miguel
  • Mezzetti, Enrico
  • Abella Ferrer, Jaume
  • Cazorla Almeida, Francisco Javier
The provision of increasingly advanced autonomous software functionalities builds on cutting-edge autonomous driving frameworks to enable modular interactions among multiple software components. This approach helps to support functional cause-effect chains from multiple sensors to actuators. The complexity of the (software) component interactions makes it more difficult to ascertain the correctness of the timing behavior of the system. This is so because traditional timing-related metrics like worst-case execution and worst-case response time do not capture the inter-dependency in cause-effect chains between the input sampling time and the time at which computation based on those inputs is performed. Complementary timing-related metrics, such as maximum reaction time and maximum data age have been considered to capture timing requirements, typically with an end-to-end scope, in cause-effect chains. These metrics have been formalized and demonstrated in ROS2-based automotive and autonomous driving setups. However, the formalization of those metrics, which is necessary for deriving analytical lower and upper bounds and monitoring them at run-time, largely depends on the execution model and semantics offered by the run-time. Any concrete application of those metrics need to be tailored and adapted to the system at hand. Apollo auto is a popular, industrial-quality, open-source autonomous driving framework that is seeing increasing adoption both for industrial and academic projects. Apollo builds on CyberRT, an ad-hoc run-time that is similar in mechanism and intent to ROS2 but differentiates from it with respect to execution model and supported semantics. In contrast to ROS2, CyberRT is highly specialized to support the Apollo AD framework, is neither extensively documented or thoroughly analysed in the literature, especially in relation to execution model and instantiation of timing-related metrics. In this work, for the first time, we provide an insightful analysis and discussion on CyberRT execution model and semantics, starting from its raw and non-extensively documented codebase. Based on the identified semantics, we elaborate a formalization of timing-related metrics on CyberRT, across different granularity scopes, namely end-to-end and node levels. In particular, we develop on the importance of node-level timing properties to intercept any latent timing misbehavior before it is too late, and it severely impacts end-to-end execution. We provide a concrete mapping of a comprehensive set of timing-related metrics to the CyberRT execution model, both at end-to-end and node level, and develop a monitoring library that allows to intercept them on the specific software stack. We exploit the proposed library on a set of Apollo autonomous driving scenarios to demonstrate its effectiveness in monitoring the considered timing metrics and to promptly intercept a subtle timing misbehavior beyond end-to-end execution scope in a representative autonomous driving stack., T his work has been supported by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101139892 (EdgeAI-Trust); by the project PLEC2023-010240, funded by MICIU/AEI /10.13039/501100011033 (CAPSUL-IA);andbytheMiguelAlcónfellowshipwithinthe”GeneraciónD”initiative,Red.es,Ministerio parala Transformación Digital ydelaFunciónPública,fortalentattraction(C005/24-EDCV1),fundedbytheEuropeanUnionNextGenerationEU funds through PRTR., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Event monitor validation in high-integrity systems

  • Pujol Torramorell, Roger
  • Vilardell Moreno, Sergi
  • Mezzetti, Enrico
  • Hassan, Mohamed
  • Abella Ferrer, Jaume
  • Cazorla Almeida, Francisco Javier
Platforms for modern embedded systems equip an increasing number of high-performance features to provide the required levels of performance. Timing analysis solutions handle the complexity of these platforms by relying on hardware event monitors (HEMs) that provide insightful information about resource utilization and, hence, contention among tasks. As a result, HEMs have become a key element to warrant a safe timing behavior of a system, for which reason they must be validated. While some initial works target HEMs validation, they consider one HEM at a time and focus on those HEMs for which an expert can establish an expected value for relatively small code snippets. In this paper, we propose a methodology for the validation of those HEMs for which a specific expected value cannot be established a priori even for simple cases and, instead, needs to be validated in conjunction with other HEMs. Our method also deals with the natural variability of the HEMs' values in high-performance platforms when collected in different experiments. We illustrate the effectiveness of our proposed technique for validating HEMs related to cache coherence in a relevant platform in the avionics domain., This work has been supported by project PLEC2023-010240 funded by MICIU/AEI/10.13039/501100011033, the European Union’s Horizon Europe research and innovation programme under grant agreement No. 101070238, and the Natural Sciences and Engineering Research Council of Canada (NSERC). The authors also thank the support of the Department of Research and Universities of the Government of Catalonia to the Smart and Safe Autonomous Systems (SSAS) Research Group, (Code: 2021 SGR 00637)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Leveraging image-based transformations to mitigate adversarial attacks in AI-based safety-critical systems

  • Caro Roca, Martí
  • Brando Guillaumes, Axel
  • Abella Ferrer, Jaume
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. https://dx.doi.org/10.1109/IOLTS65288.2025.11116992, Dual (DMR) and Triple Modular Redundancy (TMR) are widely used techniques to provide fault detection and/or tolerance capabilities in safety-critical systems through – often diverse – redundancy. However, these systems remain vulnerable to adversarial attacks, which can mislead the AI models and lead to severe consequences. In this paper, we propose enhanced DMR and TMR implementations for image-based object detection leveraging image transformations during inference to mitigate the impact of adversarial attacks, hence addressing safety and security concerns simultaneously. Our approach achieves up to 12.9% and 12.2% higher accuracy in adversarial scenarios compared to state-of-the-art solutions in DMR and TMR configurations, respectively., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num.101069595. This work is also part of the project PLEC2023-010240 funded by ICIU/AEI/10.13039/501100011033. M. Caro has received funding under grant PRE2022-102440 funded by MICIU/AEI/10.13039/501100011033 and, by ESF+., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Detecting low-density mixtures in high-quantile tails for pWCET estimation

  • Manau Corderroure, Blau
  • Vilardell Moreno, Sergi
  • Serra Mochales, Isabel
  • Mezzetti, Enrico
  • Abella Ferrer, Jaume
  • Cazorla Almeida, Francisco Javier
The variability arising from sophisticated hardware and software solutions in cutting-edge embedded products causes software to exhibit complex execution time distributions. Mixture distributions can happen, with different density (weight), as a result of inherent different features in the execution platform and multiple operational scenarios. In the context of probabilistic WCET (pWCET) analysis based on Extreme Value Theory (EVT), where identical distribution is a pre-requisite, mixtures are typically intercepted by applying stationarity tests on the full sample. Those tests, however, are instructed to detect only mixtures with sufficiently high probability (weight) and disregard low-density mixtures (which are unlikely to be preserved in the high-quantile tail of the sample) as they would prevent any form of stationarity. Nonetheless, low-density mixture distributions can persist and even exacerbate in the tail, and, when not considered, they can impair pWCET estimation in EVT-based approaches, leading to overly pessimistic or optimistic bounds. In this work, we propose TailID, an iterative point-wise approach that builds on the asymptotic convergence of the Maximum Likelihood Estimator (MLE) of the Extreme Value Index (EVI) parameter ξ to detect low-density mixture distributions on high-quantile tails and use this information to steer EVT tail selection. The benefits of the proposed method are assessed on synthetic mixture distributions and real data collected on an industrially representative embedded platform., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num. 101069595 and project PLEC2023-010240 funded by MICIU/AEI/10.13039/501100011033 (CAPSUL-IA). Authors also appreciate the support given to the Research Group SSAS (Code: 2021 SGR 00637) by the Research and University Department of the Generalitat de Catalunya. This work is partially supported by the Spanish MICIU with project PID2022-137414OB-I00., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Safety-relevant AI-based system robustification with neural network ensembles

  • Aldomà Coll, Adrià
  • Brando Guillaumes, Axel
  • Cazorla Almeida, Francisco Javier
  • Abella Ferrer, Jaume
Functional safety requirements of AI-based safety-critical applications challenge AI models, whose accuracy can be limited. In this paper, we show how using several cooperative deep learning (DL) models helps to raise global accuracy and reject making a prediction when confidence is below a pre-established threshold., The research leading to these results has received funding from the European Union’s Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num. 101069595. This work has also been supported by the Project PLEC2023-010240 funded by MICIU/AEI/10.13039/501100011033. Authors thank the support given to the Research Group SSAS (Code: 2021 SGR 00637) by the Research and University Department of the Generalitat de Catalunya., Peer Reviewed, Postprint (author's final draft)