Suchergebnisse

AbstractWith the advancement of DNNs into safety-critical applications, testing approaches for such models have gained more attention. A current direction is the search for and identification of systematic weaknesses that put safety assumptions based on average performance values at risk. Such weaknesses can take on the form of (semantically coherent) subsets or areas in the input space where a DNN performs systematically worse than its expected average. However, it is non-trivial to attribute the reason for such observed low performances to the specific semantic features that describe the subset. For instance, inhomogeneities within the data w.r.t. other (non-considered) attributes might distort results. However, taking into account all (available) attributes and their interaction is often computationally highly expensive. Inspired by counterfactual explanations, we propose an effective and computationally cheap algorithm to validate the semantic attribution of existing subsets, i.e., to check whether the identified attribute is likely to have caused the degraded performance. We demonstrate this approach on an example from the autonomous driving domain using highly annotated simulated data, where we show for a semantic segmentation model that (i) performance differences among the different pedestrian assets exist, but (ii) only in some cases is the asset type itself the reason for this reduction in the performance.

Phishing is an attack targeting to imitate the official websites of corporations such as banks, e-commerce, financial institutions, and governmental institutions. Phishing websites aim to access and retrieve users' important information such as personal identification, social security number, password, e-mail, credit card, and other account information. Several anti-phishing techniques have been developed to cope with the increasing number of phishing attacks so far. Machine learning and particularly, deep learning algorithms are nowadays the most crucial techniques used to detect and prevent phishing attacks because of their strong learning abilities on massive datasets and their state-of-the-art results in many classification problems. Previously, two types of feature extraction techniques [i.e., character embedding-based and manual natural language processing (NLP) feature extraction] were used in isolation. However, researchers did not consolidate these features and therefore, the performance was not remarkable. Unlike previous works, our study presented an approach that utilizes both feature extraction techniques. We discussed how to combine these feature extraction techniques to fully utilize from the available data. This paper proposes hybrid deep learning models based on long short-term memory and deep neural network algorithms for detecting phishing uniform resource locator and evaluates the performance of the models on phishing datasets. The proposed hybrid deep learning models utilize both character embedding and NLP features, thereby simultaneously exploiting deep connections between characters and revealing NLP-based high-level connections. Experimental results showed that the proposed models achieve superior performance than the other phishing detection models in terms of accuracy metric.

This paper describes a methodology to select the optimum combination of deep neuralnetwork and software framework for visual inference on embedded systems. As a first step, benchmarkingis required. In particular, we have benchmarked six popular network models running on four deep learningframeworks implemented on a low-cost embedded platform. Three key performance metrics have beenmeasured and compared with the resulting 24 combinations: accuracy, throughput, and power consumption.Then, application-level specifications come into play. We propose a figure of merit enabling the evaluationof each network/framework pair in terms of relative importance of the aforementioned metrics for a targetedapplication. We prove through numerical analysis and meaningful graphical representations that only areduced subset of the combinations must actually be considered for real deployment. Our approach can beextended to other networks, frameworks, and performance parameters, thus supporting system-level designdecisions in the ever-changing ecosystem of embedded deep learning technology. ; Ministerio de Economía y Competitividad (TEC2015-66878-C3-1-R) ; Junta de Andalucía (TIC 2338-2013) ; European Union Horizon 2020 (Grant 765866)

AbstractOur Visual Analytics (VA) tool ScrutinAI supports human analysts to investigate interactively model performance and data sets. Model performance depends on labeling quality to a large extent. In particular in medical settings, generation of high quality labels requires in depth expert knowledge and is very costly. Often, data sets are labeled by collecting opinions of groups of experts. We use our VA tool to analyze the influence of label variations between different experts on the model performance. ScrutinAI facilitates to perform a root cause analysis that distinguishes weaknesses of deep neural network (DNN) models caused by varying or missing labeling quality from true weaknesses. We scrutinize the overall detection of intracranial hemorrhages and the more subtle differentiation between subtypes in a publicly available data set.

ABSTRACTThe FOREX market assessment is a big challenge for investors and global risk managers. However, the present study uses daily multicurrency exchange rate returns data from 2007 to 2022 to estimate the learning returns performance of the proposed model to find a safe‐haven currency for optimal investment strategy. The categorical returns are classified into good returns (GRs), bad returns (BRs) and no returns (NRs). Therefore, the present study needs to use a one‐hot‐encoding function to convert a categorical dataset into a numeric format with TensorFlow. The present study proposes a deep neural network‐based multilayer perceptron (DNN‐based MLP) with a backpropagation algorithm to estimate the learning returns performance of the proposed model to find a safe‐haven currency for optimal investment strategy. The findings showed that currency exchange rate return 2 (CERR2) is relatively a safe‐haven currency than currency exchange rate return 1 (CERR1) and currency exchange rate return 3 (CERR3). Moreover, the findings also showed that the proposed model gives optimal learning return performance. This study may assist FOREX investors to modify their investment strategies under shed light of findings of the study. In addition, the findings of the present study may also support global risk managers to revisit their hedging strategies.

Abstract. The 2011 Tohoku-oki tsunami inundated the Joban coastal area in the Odaka region of the city of Minamisoma, up to 2818 m from the shoreline. In this study, the flow characteristics of the tsunami were reconstructed from deposits using the DNN (deep neural network) inverse model, suggesting that the tsunami inundation occurred in the Froude supercritical condition. The DNN inverse model effectively estimated the tsunami flow parameters in the Odaka region, including the maximum inundation distance, flow velocity, maximum flow depth, and sediment concentration. Despite having a few topographical anthropogenic undulations that caused the inundation height to fluctuate greatly, the reconstructed maximum flow depth and flow velocity were reasonable and close to the values reported in the field observations. The reconstructed data around the Odaka region were characterized by an extremely high velocity (12.1 m s−1). This study suggests that the large fluctuation in flow depths on the Joban Coast compared with the stable flow depths in the Sendai Plain can be explained by the inundation in the supercritical flow condition.