检索结果-内蒙古大学图书馆

Blockchain-based Edge Resource Sharing for Metaverse

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Zhilin Hu, Qin Xu, Minghui Jiang, Honglu Department of Computer & Information Science Indiana University-Purdue University Indianapolis United States School of Computer Science & Technology Shandong University China Department of Computer Science & Software Engineering Miami University United States

Although Metaverse has recently been widely studied, its practical application still faces many challenges. One of the severe challenges is the lack of sufficient resources for computing and communication on local devices, resulting in the inability to access the Metaverse services. To address this issue, this paper proposes a practical blockchain-based mobile edge computing (MEC) platform for resource sharing and optimal utilization to complete the requested offloading tasks, given the heterogeneity of servers' available resources and that of users' task requests. To be specific, we first elaborate the design of our proposed system and then dive into the task allocation mechanism to assign offloading tasks to proper servers. To solve the multiple task allocation (MTA) problem in polynomial time, we devise a learning-based algorithm. Since the objective function and constraints of MTA are significantly affected by the servers uploading the tasks, we reformulate it as a reinforcement learning problem and calculate the rewards for each state and action considering the influences of servers. Finally, numerous experiments are conducted to demonstrate the effectiveness and efficiency of our proposed system and algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

Asynchronous forensic investigative approach to recover deleted data from instant messaging applications

学校读者我要写书评

暂无评论

Asynchronous forensic investigative approach to recover dele...

2020 International Symposium on Networks, computers and Communications, ISNCC 2020

作者： Salamh, Fahad E Karabiyik, Umit Rogers, Marcus K Purdue University Department of Computer and Information Technology West LafayetteIN47906 United States

ISBN: (纸本)9781728156286

Proliferation of digital platforms specifically Instant Messaging Applications (IMAs), have introduced new challenges to digital forensic investigations. With the rapidly increased use of WhatsApp application, it is plausible to speculate that WhatsApp became a potential source of threat and/or cybercrime. Some newly added features on WhatsApp, such as 'delete for everyone', giving the users the ability to delete messages from both ends (sender and receiver), have resulted in complicating the cybercrime investigation process. Therefore, there is a need to revisit the investigation process and the structure of such updated features to be able to create a comprehensive digital forensic technique. This paper examines the forensic artifacts of the WhatsApp's 'delete for everyone' feature. This feature is a great addition to the overall usability of IMAs, however, it is also crucial to update the digital forensic investigation techniques and test the capability of commercial forensic tools in recovering forensic evidence when a new technology has been introduced. During the course of this research, we tested and validated the digital forensic methodology and compared the investigation results with forensically sound commercial tools. During the data acquisition process, we conducted physical and logical forensic acquisitions of an Android device which led to a breakthrough discovery of a SQLite file called Write-Ahead-Log (WAL) which contains the application's latest messages, including deleted (allegedly) messages. © 2020 IEEE.

关键词： Message passing

On Burial Depth of Underground Antenna in Soil Horizons for Decision Agriculture 1

学校读者我要写书评

暂无评论

5th International Conference on Internet of Things, ICIOT 2020, held as part of the Services Conference Federation, SCF 2020

作者： Salam, Abdul Raza, Usman Department of Computer and Information Technology Purdue University West LafayetteIN47906 United States

ISBN: (数字)9783030596156

ISBN: (纸本)9783030596149

Decision agriculture is the practice of accurately capturing the changing parameters of the soil including water infiltration and retention, nutrients supply, acidity, and other time changing phenomena by using the modern technologies. Using decision agriculture, fields can be irrigated more efficiently hence conserving water resources and increasing productivity. The Internet of Underground Things (IOUT) is being used to monitor the soil for smart irrigation. Moreover, the communication in wireless underground sensor networks is affected by soil characteristics such as soil texture, volumetric water content (VWC) and bulk density. These soil characteristics vary with soil type and soil horizons within a field. In this paper, we have investigated the effects of these characteristics by considering Holdrege soil series and homogeneous soil. It is shown that the consideration of soil characteristics of different soil horizons leads to 6% improved communication in wireless underground communications for smart agricultural practices. © 2020, Springer Nature Switzerland AG.

关键词： Cyber Physical System

Forensic analysis of the august smart device ecosystem

学校读者我要写书评

暂无评论

Forensic analysis of the august smart device ecosystem

2020 International Symposium on Networks, computers and Communications, ISNCC 2020

作者： Hutchinson, Shinelle Karabiyik, Umit Purdue University Department of Computer and Information Technology West LafayetteIN47907 United States

ISBN: (纸本)9781728156286

Smart Homes are becoming increasingly popular with homeowners investing in new internet-connected technologies, from smart plugs to smart appliances. One particular area where homeowners use smart devices is at the front door, as they install smart doorbells and smart locks. In this paper, we embark on an investigative journey into the August smart device ecosystem, specifically looking at the interaction between the August Smart Doorbell Pro and the August Smart Lock Pro, with their controlling app, August Home. We aim to determine what type of data forensic investigators may be able to recover about these devices and their use. We also explore how these devices interact with each other, noting any privacy issues that may be discovered. We found that a wealth of forensic data could be recovered, particularly from rooted Android devices and jailbroken iPhone devices. information about the owner of the smart device, guests who were given access to the devices, device interactions, and pictures taken by the doorbell camera, were all recoverable in plaintext. Our results also show that user's GPS coordinates associated with the lock's Auto-Unlock feature were recovered only from a rooted Android device. © 2020 IEEE.

关键词： Internet of things

An Android Case Study on Technical Anti-Forensic Challenges of WhatsApp Application 8

学校读者我要写书评

暂无评论

An Android Case Study on Technical Anti-Forensic Challenges ...

8th International Symposium on Digital Forensics and Security, ISDFS 2020

作者： Mirza, Mohammad Salamh, Fahad E. Karabiyik, Umit Purdue University Department of Computer and Information Technology West Lafayette 47907 United States

ISBN: (数字)9781728169392

ISBN: (纸本)9781728169392

Cyberbullying has become a serious concern in this Internet era with the availability of various communication technologies. While no one wishes to be a victim of cyberbullying, some of the electronic platforms, specifically Instant Messaging Applications (IMAs) such as WhatsApp, have created a safe haven for cyberbullying. As the use of WhatsApp application is globally increasing, it is extremely important to consider it being misused as a tool of cybercrime. This paper investigates some of the technical issues with WhatsApp application that could open the door to cybercrimes and pose anti-forensic challenges. In addition, we also highlight possible anti-forensic techniques for WhatsApp application through two hypothetical case scenarios. Moreover, we propose a validated solution to the 'delete for everyone' feature of WhatsApp by presenting a demo mobile application that recovers any deleted messages even after block status. © 2020 IEEE.

关键词： Android (operating system)

High-Efficiency Neural Video Compression via Hierarchical Predictive Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lu, Ming Duan, Zhihao Cong, Wuyang Ding, Dandan Zhu, Fengqing Ma, Zhan The School of Electronic Science and Engineering Nanjing University Jiangsu Nanjing210023 China The Elmore Family School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States The School of Information Science and Technology Hangzhou Normal University Zhejiang Hangzhou311121 China

The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods but also impressive complexity efficiency, enabling real-time processing with a significantly smaller memory footprint on standard GPUs. These remarkable advancements stem from the use of hierarchical predictive coding. Each video frame is uniformly transformed into multiscale representations through hierarchical variational autoencoders. For a specific scale's feature representation of a frame, its corresponding latent residual variables are generated by referencing lower-scale spatial features from the same frame and then conditionally entropy-encoded using a probabilistic model whose parameters are predicted using same-scale temporal reference from previous frames and lower-scale spatial reference of the current frame. This feature-space processing operates from the lowest to the highest scale of each frame, completely eliminating the need for the complexity-intensive motion estimation and compensation techniques that have been standard in video codecs for decades. The hierarchical approach facilitates parallel processing, accelerating both encoding and decoding, and supports transmission-friendly progressive decoding, making it particularly advantageous for networked video applications in the presence of packet loss. Source codes will be made available. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

Graph-of-tweets: A graph merging approach to sub-event identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jing, Xiaonan Rayz, Julia Taylor Computer and Information Technology Purdue University West LafayetteIN United States

Graph structures are powerful tools for modeling the relationships between textual elements. Graph-of-Words (GoW) has been adopted in many Natural Language tasks to encode the association between terms. However, GoW provides few document-level relationships in cases when the connections between documents are also essential. For identifying sub-events on social media like Twitter, features from both word- and document-level can be useful as they supply different information of the event. We propose a hybrid Graph-of-Tweets (GoT) model which combines the word- and document-level structures for modeling Tweets. To compress large amount of raw data, we propose a graph merging method which utilizes FastText word embeddings to reduce the GoW. Furthermore, we present a novel method to construct GoT with the reduced GoW and a Mutual information (MI) measure. Finally, we identify maximal cliques to extract popular sub-events. Our model showed promising results on condensing lexical-level information and capturing keywords of sub-events. © 2021, CC BY-NC-ND.

关键词： Embeddings

Exploring lexical irregularities in hypothesis-only models of natural language inference

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Qingyuan Zhang, Yi Misra, Kanishka Rayz, Julia Taylor Computer and Information Technology Purdue University West LafayetteIN United States

Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) is the task of predicting the entailment relation between a pair of sentences (premise and hypothesis). This task has been described as "a valuable testing ground for the development of semantic representations" [1], and is a key component in natural language understanding evaluation benchmarks. Models that understand entailment should encode both, the premise and the hypothesis. However, experiments by Poliak et al. [2] revealed a strong preference of these models towards patterns observed only in the hypothesis, based on a 10 dataset comparison. Their results indicated the existence of statistical irregularities present in the hypothesis that bias the model into performing competitively with the state of the art. While recast datasets provide large scale generation of NLI instances due to minimal human intervention, the papers that generate them do not provide fine-grained analysis of the potential statistical patterns that can bias NLI models. In this work, we analyze hypothesis-only models trained on one of the recast datasets provided in Poliak et al. [2] for word-level patterns. Our results indicate the existence of potential lexical biases that could contribute to inflating the models’ performance. © 2021, CC BY-NC-ND.

关键词： Semantics

Rank-based Decomposable Losses in Machine Learning: A Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Shu Wang, Xin Lyu, Siwei The Department of Computer Information and Graphics Technology Purdue School of Engineering and Technology Indiana University-Purdue University IndianapolisIN46202 United States The Heinz College of Information Systems and Public Policy Carnegie Mellon University PittsburghPA15213 United States The Department of Computer Science and Engineering University at Buffalo SUNY BuffaloNY14260 United States

Recent works have revealed an essential paradigm in designing loss functions that differentiate individual losses vs. aggregate losses. The individual loss measures the quality of the model on a sample, while the aggregate loss combines individual losses/scores over each training sample. Both have a common procedure that aggregates a set of individual values to a single numerical value. The ranking order reflects the most fundamental relation among individual values in designing losses. In addition, decomposability, in which a loss can be decomposed into an ensemble of individual terms, becomes a significant property of organizing losses/scores. This survey provides a systematic and comprehensive review of rank-based decomposable losses in machine learning. Specifically, we provide a new taxonomy of loss functions that follows the perspectives of aggregate loss and individual loss. We identify the aggregator to form such losses, which are examples of set functions. We organize the rank-based decomposable losses into eight categories. Following these categories, we review the literature on rank-based aggregate losses and rank-based individual losses. We describe general formulas for these losses and connect them with existing research topics. We also suggest future research directions spanning unexplored, remaining, and emerging issues in rank-based decomposable losses. Copyright © 2022, The Authors. All rights reserved.

关键词： Aggregates