Biblio

Common Vulnerabilities and Exposures (CVE) databases contain information about vulnerabilities of software products and source code. If individual elements of CVE descriptions can be extracted and structured, then the data can be used to search and analyze CVE descriptions. Herein we propose a method to label each element in CVE descriptions by applying Named Entity Recognition (NER). For NER, we used BERT, a transformer-based natural language processing model. Using NER with machine learning can label information from CVE descriptions even if there are some distortions in the data. An experiment involving manually prepared label information for 1000 CVE descriptions shows that the labeling accuracy of the proposed method is about 0.81 for precision and about 0.89 for recall. In addition, we devise a way to train the data by dividing it into labels. Our proposed method can be used to label each element automatically from CVE descriptions.

Deep learning models rely on single word features and location features of text to achieve good results in text relation extraction tasks. However, previous studies have failed to make full use of semantic information contained in sentence dependency syntax trees, and data sparseness and noise propagation still affect classification models. The BERT(Bidirectional Encoder Representations from Transformers) pretrained language model provides a better representation of natural language processing tasks. And entity enhancement methods have been proved to be effective in relation extraction tasks. Therefore, this paper proposes a combination of the shortest dependency path and entity-enhanced BERT pre-training language model for model construction to reduce the impact of noise terms on the classification model and obtain more semantically expressive feature representation. The algorithm is tested on SemEval-2010 Task 8 English relation extraction dataset, and the F1 value of the final experiment can reach 0. 881.

Multi-label image classification task aims to predict multiple object labels in a given image and faces the challenge of variable-sized objects. Limited by the size of CNN convolution kernels, existing CNN-based methods have difficulty capturing global dependencies and effectively fusing multiple layers features, which is critical for this task. Recently, transformers have utilized multi-head attention to extract feature with long range dependencies. Inspired by this, this paper proposes a Cross-layer Aggregation with Transformers (CAT) framework, which leverages transformers to capture the long range dependencies of CNN-based features with Long Range Dependencies module and aggregate the features layer by layer with Cross-Layer Fusion module. To make the framework efficient, a multi-head pre-max attention is designed to reduce the computation cost when fusing the high-resolution features of lower-layers. On two widely-used benchmarks (i.e., VOC2007 and MS-COCO), CAT provides a stable improvement over the baseline and produces a competitive performance.

Recent advances in deep learning typically, with the introduction of transformer based models has shown massive improvement and success in many Natural Language Processing (NLP) tasks. One such area which has leveraged immensely is conversational agents or chatbots in open-ended (chit-chat conversations) and task-specific (such as medical or legal dialogue bots etc.) domains. However, in the era of automation, there is still a dearth of works focused on one of the most relevant use cases, i.e., tutoring dialog systems that can help students learn new subjects or topics of their interest. Most of the previous works in this domain are either rule based systems which require a lot of manual efforts or are based on multiple choice type factual questions. In this paper, we propose EDICA (Educational Domain Infused Conversational Agent), a language tutoring Virtual Agent (VA). EDICA employs two mechanisms in order to converse fluently with a student/user over a question and assist them to learn a language: (i) Student/Tutor Intent Classification (SIC-TIC) framework to identify the intent of the student and decide the action of the VA, respectively, in the on-going conversation and (ii) Tutor Response Generation (TRG) framework to generate domain infused and intent/action conditioned tutor responses at every step of the conversation. The VA is able to provide hints, ask questions and correct student's reply by generating an appropriate, informative and relevant tutor response. We establish the superiority of our proposed approach on various evaluation metrics over other baselines and state of the art models.

Speech recognition technology has been applied to all aspects of our daily life, but it faces many security issues. One of the major threats is the adversarial audio examples, which may tamper the recognition results of the acoustic speech recognition system (ASR). In this paper, we propose an adversarial detection framework to detect adversarial audio examples. The method is based on the transformer self-attention mechanism. Spectrogram features are extracted from the audio and divided into patches. Position information are embedded and then fed into transformer encoder. Experimental results show that the method achieves good performance with the detection accuracy of above 96.5% under the white-box attacks and blackbox attacks, and noisy circumstances. Even when detecting adversarial examples generated by the unknown attacks, it also achieves satisfactory results.

The electrical grid connects all the generating stations to supply uninterruptible power to the consumers. With the advent of technology, smart sensors and communication are integrated with the existing grid to behave like a smart system. This smart grid is a two-way communication that connects the consumers and producers. It is a connected smart network that integrates electricity generation, transmission, substation, distribution, etc. In this smart grid, clean, reliable power with a high-efficiency rate of transmission is available. In this paper, a highly efficient smart management system of a smart grid with overall protection is proposed. This management system checks and monitors the parameters periodically. This future technology also develops a smart transformer with ac and dc compatibility, for self-protection and for the healing process.

XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a single explanation, which fails to account for the diversity of human thoughts and experiences in language. This paper thus addresses this gap, by proposing a generative XAI framework, INTERACTION (explain aNd predicT thEn queRy with contextuAl CondiTional varIational autO-eNcoder). Our novel framework presents explanation in two steps: (step one) Explanation and Label Prediction; and (step two) Diverse Evidence Generation. We conduct intensive experiments with the Transformer architecture on a benchmark dataset, e-SNLI [1]. Our method achieves competitive or better performance against state-of-the-art baseline models on explanation generation (up to 4.7% gain in BLEU) and prediction (up to 4.4% gain in accuracy) in step one; it can also generate multiple diverse explanations in step two.

The fundamental limits of high-current conduction and response of metal conductors to large, fast current pulses are of interest to high-speed fuses, exploding wires and foils, and magnetically driven dynamic material property and inertial confinement fusion experiments. A collaboration between the University of Nevada, Reno, University of New Mexico, and Sandia National Laboratory has fielded an electrically thick (R 400-μm \textbackslashtextgreater skin-depth) cylindrical metal rod platform in a Z-pinch configuration driven by the Sandia 100-ns, 900-kA Mykonos linear transformer driver 1 . Photonic Doppler velocimetry (PDV) measuring the expansion velocity of the uncoated surface of aluminum rods 2 was used to benchmark equation of state (EOS) and electrical conductivity models used in magnetohydrodynamics simulations using the Los Alamos National Laboratory (LANL) code FLAG 3 . The metal surface was found to expand along the liquid-vapor coexistence curve in density-temperature space for 90 ns of the rod’s expansion for both tabular EOSs with Van der Waals loops and with Maxwell constructions under the vapor dome. As the slope of the coexistence curve varies across EOS models, the metal surface in simulation was found to heat and expand at different rates depending on the model used. The expansion velocities associated with EOS models were then compared against the PDV data to validate the EOS used in simulations of similar systems. Here, the most recent aluminum EOS (SESAME 93722) 4 was found to drive a simulated velocity that best compared with the experimental data due to its relatively steep coexistence curve and high critical point.

Graphs have proved to be a promising data structure to solve complex problems in various domains. Graphs store data in an associative manner which is analogous to the manner in which humans store memories in the brain. Generathe chatbots lack the ability to recall details revealed by the user in long conversations. To solve this problem, we have used graph-based memory to recall-related conversations from the past. Thus, providing context feature derived from query systems to generative systems such as OpenAI GPT. Using graphs to detect important details from the past reduces the total amount of processing done by the neural network. As there is no need to keep on passingthe entire history of the conversation. Instead, we pass only the last few pairs of utterances and the related details from the graph. This paper deploys this system and also demonstrates the ability to deploy such systems in real-world applications. Through the effective usage of knowledge graphs, the system is able to reduce the time complexity from O(n) to O(1) as compared to similar non-graph based implementations of transfer learning- based conversational agents.

With the development of artificial intelligence, facial expression recognition (FER) has greatly improved performance in deep learning, but there is still a lot of room for improvement in the study of combining attention to focus the network on key parts of the face. For facial expression recognition, this paper designs a network model, which use spatial transformer network to transform the input image firstly, and then adding channel attention and spatial attention to the convolutional network. In addition, in this paper, the GELU activation function is used in the convolutional network, which improves the recognition rate of facial expressions to a certain extent.

Cyber-defense systems are being developed to automatically ingest Cyber Threat Intelligence (CTI) that contains semi-structured data and/or text to populate knowledge graphs. A potential risk is that fake CTI can be generated and spread through Open-Source Intelligence (OSINT) communities or on the Web to effect a data poisoning attack on these systems. Adversaries can use fake CTI examples as training input to subvert cyber defense systems, forcing their models to learn incorrect inputs to serve the attackers' malicious needs. In this paper, we show how to automatically generate fake CTI text descriptions using transformers. Given an initial prompt sentence, a public language model like GPT-2 with fine-tuning can generate plausible CTI text that can mislead cyber-defense systems. We use the generated fake CTI text to perform a data poisoning attack on a Cybersecurity Knowledge Graph (CKG) and a cybersecurity corpus. The attack introduced adverse impacts such as returning incorrect reasoning outputs, representation poisoning, and corruption of other dependent AI-based cyber defense systems. We evaluate with traditional approaches and conduct a human evaluation study with cyber-security professionals and threat hunters. Based on the study, professional threat hunters were equally likely to consider our fake generated CTI and authentic CTI as true.

Malware poses a threat to computing systems worldwide, and security experts work tirelessly to detect and classify malware as accurately and quickly as possible. Since malware can use evasion techniques to bypass static analysis and security mechanisms, dynamic analysis methods are more useful for accurately analyzing the behavioral patterns of malware. Previous studies showed that malware behavior can be represented by sequences of executed system calls and that machine learning algorithms can leverage such sequences for the task of malware classification (a.k.a. malware categorization). Accurate malware classification is helpful for malware signature generation and is thus beneficial to antivirus vendors; this capability is also valuable to organizational security experts, enabling them to mitigate malware attacks and respond to security incidents. In this paper, we propose an improved methodology for malware classification, based on analyzing sequences of system calls invoked by malware in a dynamic analysis environment. We show that adding an attention mechanism to a LSTM model improves accuracy for the task of malware classification, thus outperforming the state-of-the-art algorithm by up to 6%. We also show that the transformer architecture can be used to analyze very long sequences with significantly lower time complexity for training and prediction. Our proposed method can serve as the basis for a decision support system for security experts, for the task of malware categorization.

The circulating current in the D-winding may cause primary current waveform distortion, and the reliability of the restraint criterion based on the typical magnetizing inrush current characteristics will be affected. The magnetizing inrush current with typical characteristics is the sum of primary current and circulating current. Using the circulating current to compensate the primary current can improve the reliability of the differential protection. When the phase is not saturated, the magnetizing inrush current is about zero. Therefore, the primary current of unsaturated phase can be replaced by the opposite of the circulating current. Based on this, an engineering practical calculation method for circulating current is proposed. In the method, the segmented primary currents are used to replace the circulating current. Phasor analysis is used to demonstrate the application effect of this method when remanence coefficients are different. The method is simple and practical, and has strong applicability and high reliability. Simulation and recorded waveforms have verified the effectiveness of the method.

In recent years, there have been situations in which the zero-sequence protection of the transformer has been incorrectly operated due to the converter transformer energizing or fault recovery. For converter transformers, maloperation may also occur. However, there is almost no theoretical research on the zero-mode inrush currents of converter transformers. This paper studies the characteristics of the zero-mode inrush currents of the converter transformers, including the relationship between the amplitude and attenuation characteristics of the zero-mode inrush currents of converter transformers, and their relationship with the system resistance, remanence, and closing angle. First, based on the T-type equivalent circuit of the transformer, the equivalent circuit of the zero-mode inrush current of each transformer is obtained. On this basis, the amplitude relationship of the zero-mode inrush currents of different converter transformers is obtained: the zero-mode inrush current of the energizing pole YY transformer becomes larger than the YD transformer, the energized pole YD becomes greater than the YY transformer, and the YY transformer zero-mode inrush current rises from 0. It is also analyzed that the sympathetic interaction will make the attenuation of the converter transformer zero-mode inrush current slower. The system resistance mainly affects the initial attenuation speed, and the later attenuation speed is mainly determined by the converter transformer leakage reactance. Finally, PSCAD modeling and simulation are carried out to verify the accuracy of the theoretical analysis.