13 results
Filters
Settings
Now showing1 - 10 of 13
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Efficient adversarial generation through selective SBFL guidance and automated sub-model strategyFast Gradient Sign Method (FGSM) is an effective method for generating adversarial inputs for neural networks, but it is memory-intensive. DeepFault reduces the memory costs of FGSM by transferring Spectrum-Based Fault Localization (SBFL) to neural networks. SBFL is a technique traditionally using the execution trace of a program to iden-tify suspicious code locations that are likely to contain faults. DeepFault employs SBFL to identify neurons in a neural network that are likely to be responsible for misclassifications to guide FGSM. We propose an adjustable SBFL-guided adversarial input generation approach that addresses both memory and runtime efficiency challenges for sequential classification models. Our contributions include: (1) an automated and adjustable sub-model strategy that selects smaller model configurations for input synthesis, reducing both memory overhead and computational effort, (2) vector-based hit-spectrum computation using GPU-accelerated operations to significantly reduce computation time (3) targeted adversarial input generation enabling modifications in favor of specific target classes, and (4) comprehensive experimental evaluation on contemporary sequential neural network architectures. Our evaluation demonstrates substantial improvements over existing methods: up to 4.7× memory reduction compared to FGSM and up to 301× speedup over DeepFault while maintaining comparable adversarial input quality. All experiments complete within tens of seconds, demonstrating practical scalability for contemporary models.Publicationtype: Conference Paper11 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Multimodal Object Analysis with Auditory and Tactile Sensing Using Recurrent Neural Networks(2021-12); ; ; Robots are usually equipped with many different sensors that need to be integrated. While most research is focused on the integration of vision with other senses, we successfully integrate tactile and auditory sensor data from a complex robotic system. Herein, we train and evaluate a neural network for the classification of the content of eight optically identical medicine containers. To investigate the relevance of the tactile modality in classification under realistic conditions, we apply different noise levels to the audio data. Our results show significantly higher robustness to acoustic noise with the combined multimodal network than with the unimodal audio based counterpart.Publicationtype: Conference Paper46 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , On the Transferability of Neural Models of Morphological Analogies(Springer, 2021-09); ; ; ; Analogical proportions are statements expressed in the form “A is to B as C is to D” and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). In this paper, we focus on morphological tasks and we propose a deep learning approach to detect morphological analogies. We present an empirical study to see how our framework transfers across languages, and that highlights interesting similarities and differences between these languages. In view of these results, we also discuss the possibility of building a multilingual morphological model.Publicationtype: Conference Paper27 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Industrial federated learning – requirements and system design(2020-01); ; ; Federated Learning (FL) is a very promising approach for improving decentralized Machine Learning (ML) models by exchanging knowledge between participating clients without revealing private data. Nevertheless, FL is still not tailored to the industrial context as strong data similarity is assumed for all FL tasks. This is rarely the case in industrial machine data with variations in machine type, operational- and environmental conditions. Therefore, we introduce an Industrial Federated Learning (IFL) system supporting knowledge exchange in continuously evaluated and updated FL cohorts of learning tasks with sufficient data similarity. This enables optimal collaboration of business partners in common ML problems, prevents negative knowledge transfer, and ensures resource optimization of involved edge devices.Publicationtype: Conference Paper77 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Advances in service-oriented and cloud computing(Springer, 2018)Publicationtype: Conference Proceedings21 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Theta architecture: Preserving the quality of analytics in data-driven systems(Springer, 2017-09); ; ; ; With the recent advances in Big Data storage and processing, there is a real potential of data-driven software systems, i.e., systems that employ analysis of large amounts of data to inform their runtime decisions. However, for these decisions to be trustworthy and dependable, one needs to deal with the well-known challenges on the data analysis domain: Data scarcity, low-quality of data available for analysis, low veracity of data and subsequent analysis results, data privacy constraints that hinder the analysis. A promising solution is to introduce flexibility in the data analytics part of the system enabling optimization at runtime of the algorithms and data streams based on the combination of veracity, privacy and scarcity in order to preserve the target level of quality of the data-driven decisions. In this paper, we investigate this solution by providing an adaptive reference architecture and illustrate its applicability with an example from the traffic management domain.Publicationtype: Conference Paper14 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Preface - 5th European Conference on Service-Oriented and Cloud Computing, ESOCC 2016Publicationtype: Editorial21 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Some modelling aspects of aggregation kernels and the aggregation population balance equations(Springer, 2012-08); ; ; ; Aggregation is one of the important processes in chemical and process engineering. To model this process aggregation population balance equation is widely used. The aggregation kernel is one of the most effective parameter of this aggregation equation. This is usually defined as the product of the aggregation efficiency and collision frequency functions. Several authors attempted to model the aggregation kernel using different approaches like theoretical, experimental and empirical approaches. In the present paper we are giving some important modelling aspects of these kernels. One can use these modelling aspects in other variants of the population balance equations with breakage, nucleation, growth, ..., etc.Publicationtype: Conference Paper37 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Requirements-driven runtime reconfiguration for security(Springer, 2011-05); ; ; The boundary between development time and run time of eternal software intensive applications is fading. In particular, these systems are characterized by the necessity to evolve requirements continuously, even after the deployment. In this paper we focus on the evolution of security requirements and introduce an integrated process to drive runtime reconfiguration from requirements changes. This process relies on two key proposals: systematic strategies to evolve architecture models according to security requirements evolution and the combination of reflective middleware and models@runtime for runtime reconfiguration.Publicationtype: Conference Paper17 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , A configurable integrated circuit for biomedical signal acquisition(Springer, 2011-01); ; ; ; Publicationtype: Conference Paper34