As the technology advances, an increase in the attacks to manipulate or extract data illegally has also risen. This also includes one such attack known as Address Resolution protocol cache spoofing attack. The Address...
详细信息
ISBN:
(数字)9798331508456
ISBN:
(纸本)9798331508463
As the technology advances, an increase in the attacks to manipulate or extract data illegally has also risen. This also includes one such attack known as Address Resolution protocol cache spoofing attack. The Address Resolution protocol Spoofer conducts an in-depth exploration into one of the most significant security vulnerabilities identified in local networks, namely Address resolution protocol cache poisoning. The study implements a system which uses a Python based tool which is able to simulate Address Resolution protocol spoofing attacks on the network traffic of two hosts through a Python library known as the Scapy library. This tool allows the execution of Man In The Middle attacks by forging Address Resolution protocol replies and changing the stream of traffic without setting off any alarm by the user. The tool also has a detection mechanism that alerts the users as soon as it detects attempted spoofing; which hence identifies both the offender and the defensive capabilities in Address Resolution protocol spoofing. Additionally, another layer of security is added by user-defined encryption and decryption of the message being delivered. The study has resulted in a secure network, protecting the data from ARP spoofing.
Facial recognition is in use for the past decade there are many applications that needs facial expression to learn the human behaviour and emotions for certain activities. Facial recognition is in a development phase ...
详细信息
Today, many students are having a hard time learning to speak the English language and the problem is even worse for those in rural areas, where both teachers and resources are rare. We are trying to break this dispar...
Today, many students are having a hard time learning to speak the English language and the problem is even worse for those in rural areas, where both teachers and resources are rare. We are trying to break this disparity and provide better resources for those in need utilizing Artificial Intelligence and Natural Language Processing (NLP) to contribute to the SDG4 Quality and Inclusive Education. In this paper, we present the idea of how we developed Chatbot named BuddyBot Utilizing OpenAI Generative Pre-Trained Transformer 2 (GPT-2) and Google Text-to-Text Transfer Transformer (FLAN-T5) models. This system incorporates diverse datasets for fine-tuning and specialized tasks in English language learning. BuddyBot follows a five-phase architecture - User interface, Pre-processing, Natural Language Processing (NLP) stack, language generation engine and adaptive learning personalization. The E-Learn web-based interface offers interactive courses with BuddyBot assistance, emphasizing adaptive learning personalization. Dataset preprocessing includes tokenization, sentiment analysis, and specialized formatting. The NLP stack integrates GPT-2 and FLAN-T5 models into the framework, maintaining dialogue structure and personalization. Validation tests reveal model effectiveness, with reduced training loss (0.778 to 0.414 by epoch 8) and increased accuracy (0.810 training, 0.792 validation). Overall, BuddyBot's robust methodology and validation results showcase its efficacy in providing personalized English language learning experiences.
Intent classification plays a crucial role in applications such as virtual assistants and chatbots, enabling an accurate determination of the user's intention and providing relevant responses. Minimal supervision ...
详细信息
ISBN:
(数字)9798331544607
ISBN:
(纸本)9798331544614
Intent classification plays a crucial role in applications such as virtual assistants and chatbots, enabling an accurate determination of the user's intention and providing relevant responses. Minimal supervision models that train from minimal labeled data have become important since they can train models using less amount of data as manually labeling data is time-consuming. To address this problem, the proposed model utilizes a few-shot learning mechanism approach using a metalearning architecture for intent classification. Model-Agnostic Meta Learning model is implemented to enhance generalization given the scenario of constrained labeled samples. Model Agnostic Meta Learning is tested using uniform and complexity aware optimal sampling based methods to assess the impact of data imbalance and robustness of the model. The experimental results on the Banking77 dataset show that the Meta Agnostic Meta Learning architectures in a complexity aware non-uniform sampling setting are able to achieve 100 % of the results achieved by full train models when integrated with ML models. DL models on the other hand did not report a considerable enhancement when migrated from a uniform to a non-uniform sampling setting.
Understanding and learning the actor-to-X interactions (AXIs), such as those between the focal vehicles (actor) and other traffic participants, such as other vehicles and pedestrians, as well as traffic environments l...
详细信息
Understanding and learning the actor-to-X interactions (AXIs), such as those between the focal vehicles (actor) and other traffic participants, such as other vehicles and pedestrians, as well as traffic environments like the city or road map, is essential for the development of a decision-making model and the simulation of autonomous driving. Existing practices on imitation learning (IL) for autonomous driving simulation, despite the advances in the model learnability, have not accounted for fusing and differentiating the heterogeneous AXIs in complex road environments. Furthermore, how to further explain the hierarchical structures within the complex AXIs remains largely *** meet these challenges, we propose HGIL, an interaction-aware and hierarchically-explainable Heterogeneous Graph-based Imitation Learning approach for autonomous driving simulation. We have designed a novel heterogeneous interaction graph (HIG) to provide local and global representation as well as awareness of the AXIs. Integrating the HIG as the state embeddings, we have designed a hierarchically-explainable generative adversarial imitation learning approach, with local sub-graph and global cross-graph attention, to capture the interaction behaviors and driving decision-making processes. Our data-driven simulation and explanation studies based on the Argoverse v2 dataset (with a total of 40,000 driving scenes) have corroborated the accuracy (e.g., lower displacement errors compared to the state-of-the-art (SOTA) approaches) and explainability of HGIL in learning and capturing the complex AXIs.
Intent classification plays a crucial role in applications such as virtual assistants and chatbots, enabling an accurate determination of the user's intention and providing relevant responses. Minimal supervision ...
详细信息
With the emergence of diverse languages, cultural nuances, and code-mixed content, detecting offensive language on social media has become critical. This paper addresses these challenges with the help of the multiling...
详细信息
ISBN:
(数字)9798331537555
ISBN:
(纸本)9798331537562
With the emergence of diverse languages, cultural nuances, and code-mixed content, detecting offensive language on social media has become critical. This paper addresses these challenges with the help of the multilingual T5 (mT5) model, which has been fine-tuned to detect offensive language in code-mixed multilingual texts. The system is designed as a browser-based web extension that offers real-time detection by blurring or concealing offensive content, which leads to continuous improvement. It also integrates user-centric features that enable users to provide feedback on the accuracy of offensive content detection and report any instances of offensive language that go undetected, supporting continuous enhancement. This user-centric approach presents an accurate, efficient, and context-aware offensive language detection experience, which leads to safer and more secure online environments for different communities.
The 5G demonstrations in a business has a significant role in today’s fast-moving *** in 5G,drives a wireless system intended at an enormously high data rate,lower energy,low latency,and *** this reason,routing proto...
详细信息
The 5G demonstrations in a business has a significant role in today’s fast-moving *** in 5G,drives a wireless system intended at an enormously high data rate,lower energy,low latency,and *** this reason,routing protocols of MANET have the possibility of being fundamentally flexible,high performance,and *** 5G communication aims to afford higher data rates and significantly low Over-The-Air *** through supplementary ACO routing processes,a security-aware,fuzzy improved ant colony routing optimization protocol is proposed in *** goal is to develop aMANET routing protocol that could provide a stable packet transmission ratio,less overhead connectivity,and low end-to-end latency in shared standard scenarios and attack *** demonstrates effective results with hybrid architecture and proved to be effective than other state-of-the-art routing protocols of MANETs,like AODV,its routing organization implemented through Optimized Fuzzy based ACO Algorithm for ***-wavelengths are required to perform a significant role in *** research proposed to test the efficiency of MANET consisting of only mmWave User *** reduced packet transmission loss of UEs withmmWave,meaning well-transmitted SNR leads directly to a better packet delivery *** verify results,simulation using the NS-3 simulator mmWave module is used.
The rising interconnectivity of digital systems has brought about the challenges of network security as high risks of data theft and unauthorized access through intrusions in networks. This paper details the developme...
详细信息
ISBN:
(数字)9798331523893
ISBN:
(纸本)9798331523909
The rising interconnectivity of digital systems has brought about the challenges of network security as high risks of data theft and unauthorized access through intrusions in networks. This paper details the development of a Network Intrusion Detection System that uses deep learning techniques and is designed to detect normal as well as anomalous activities within the network, such as zero-Day vulnerabilities, as discussed has proven that this model was capable of obtaining excellent accuracy, up to 99.25%, with precision and recall metric being well achieved, owed to advanced techniques, in this case, hyperparameter tuning. This will mean the model's capability to clearly differentiate legitimate and malicious traffic. In addition, explainable AI techniques such as SHAP and LIME deliver insights into the contributions or importance of various features about a model's decision-making.
Cross-resolution person re-identification(CR-ReID) seeks to overcome the challenge of retrieving and matching specific person images across cameras with varying resolutions. Numerous existing studies utilize establish...
详细信息
暂无评论