As healthcare systems worldwide continue to grapple with the challenges of interoperability, data security, and accessibility, integrating emerging technologies becomes imperative. This paper investigates the implementation of blockchain technology, specifically Hyperledger Fabric, for Electronic Health Records (EHR) management at Frere Hospital in the Eastern Cape province of South Africa. The paper examines the benefits and challenges of integrating blockchain into healthcare information systems. Hyperledger Fabric's modular architecture is harnessed to create a secure, transparent, and decentralized platform for storing, managing, and sharing EHRs among stakeholders. The study used a mixed-methods approach, integrating case studies and data collection methods through observation and informal questions, with the specific goal of understanding current record management methods and challenges. This method offers practical insights and validates the approach. The result demonstrates the role of blockchain in transforming healthcare, framed within a rigorous exploration and analysis. The findings of this study have broader implications for healthcare institutions seeking advanced solutions to address the persistent challenges in electronic health record management. Ultimately, the research underscores the transformative potential of blockchain technology in healthcare settings, fostering trust, security, and efficiency in the management of sensitive patient data.
{"title":"Blockchain in Healthcare: Implementing Hyperledger Fabric for Electronic Health Records at Frere Provincial Hospital","authors":"Abayomi Agbeyangi, Olukayode Oki, Aphelele Mgidi","doi":"arxiv-2407.15876","DOIUrl":"https://doi.org/arxiv-2407.15876","url":null,"abstract":"As healthcare systems worldwide continue to grapple with the challenges of\u0000interoperability, data security, and accessibility, integrating emerging\u0000technologies becomes imperative. This paper investigates the implementation of\u0000blockchain technology, specifically Hyperledger Fabric, for Electronic Health\u0000Records (EHR) management at Frere Hospital in the Eastern Cape province of\u0000South Africa. The paper examines the benefits and challenges of integrating\u0000blockchain into healthcare information systems. Hyperledger Fabric's modular\u0000architecture is harnessed to create a secure, transparent, and decentralized\u0000platform for storing, managing, and sharing EHRs among stakeholders. The study\u0000used a mixed-methods approach, integrating case studies and data collection\u0000methods through observation and informal questions, with the specific goal of\u0000understanding current record management methods and challenges. This method\u0000offers practical insights and validates the approach. The result demonstrates\u0000the role of blockchain in transforming healthcare, framed within a rigorous\u0000exploration and analysis. The findings of this study have broader implications\u0000for healthcare institutions seeking advanced solutions to address the\u0000persistent challenges in electronic health record management. Ultimately, the\u0000research underscores the transformative potential of blockchain technology in\u0000healthcare settings, fostering trust, security, and efficiency in the\u0000management of sensitive patient data.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141773817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We aim to evaluate the efficacy of traditional machine learning and large language models (LLMs) in classifying anxiety and depression from long conversational transcripts. We fine-tune both established transformer models (BERT, RoBERTa, Longformer) and more recent large models (Mistral-7B), trained a Support Vector Machine with feature engineering, and assessed GPT models through prompting. We observe that state-of-the-art models fail to enhance classification outcomes compared to traditional machine learning methods.
{"title":"Evaluating Large Language Models for Anxiety and Depression Classification using Counseling and Psychotherapy Transcripts","authors":"Junwei Sun, Siqi Ma, Yiran Fan, Peter Washington","doi":"arxiv-2407.13228","DOIUrl":"https://doi.org/arxiv-2407.13228","url":null,"abstract":"We aim to evaluate the efficacy of traditional machine learning and large\u0000language models (LLMs) in classifying anxiety and depression from long\u0000conversational transcripts. We fine-tune both established transformer models\u0000(BERT, RoBERTa, Longformer) and more recent large models (Mistral-7B), trained\u0000a Support Vector Machine with feature engineering, and assessed GPT models\u0000through prompting. We observe that state-of-the-art models fail to enhance\u0000classification outcomes compared to traditional machine learning methods.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141743473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A vaccine passport serves as documentary proof, providing passport holders with greater freedom while roaming around during pandemics. It confirms vaccination against certain infectious diseases like COVID-19, Ebola, and flu. The key challenges faced by the digital vaccine passport system include passport forgery, unauthorized data access, and inaccurate information input by vaccination centers. Privacy concerns also need to be addressed to ensure that the user's personal identification information (PII) is not compromised. Additionally, it is necessary to track vaccine vials or doses to verify their authenticity, prevent misuse and illegal sales, as well as to restrict the illicit distribution of vaccines. To address these challenges, we propose a Blockchain-Enabled Secure Vaccine Passport System, leveraging the power of smart contracts. Our solution integrates off-chain and on-chain cryptographic computations, facilitating secure communication among various entities. We have utilized the InterPlanetary File System (IPFS) to store encrypted vaccine passports of citizens securely. Our prototype is built on the Ethereum platform, with smart contracts deployed on the Sepolia Test network, allowing for performance evaluation and validation of the system's effectiveness. By combining IPFS as a distributed data storage platform and Ethereum as a blockchain platform, our solution paves the way for secure, efficient, and globally interoperable vaccine passport management, supporting comprehensive vaccination initiatives worldwide.
{"title":"SecureVAX: A Blockchain-Enabled Secure Vaccine Passport System","authors":"Debendranath Das, Sushmita Ruj, Subhamoy Maitra","doi":"arxiv-2407.13852","DOIUrl":"https://doi.org/arxiv-2407.13852","url":null,"abstract":"A vaccine passport serves as documentary proof, providing passport holders\u0000with greater freedom while roaming around during pandemics. It confirms\u0000vaccination against certain infectious diseases like COVID-19, Ebola, and flu.\u0000The key challenges faced by the digital vaccine passport system include\u0000passport forgery, unauthorized data access, and inaccurate information input by\u0000vaccination centers. Privacy concerns also need to be addressed to ensure that\u0000the user's personal identification information (PII) is not compromised.\u0000Additionally, it is necessary to track vaccine vials or doses to verify their\u0000authenticity, prevent misuse and illegal sales, as well as to restrict the\u0000illicit distribution of vaccines. To address these challenges, we propose a\u0000Blockchain-Enabled Secure Vaccine Passport System, leveraging the power of\u0000smart contracts. Our solution integrates off-chain and on-chain cryptographic\u0000computations, facilitating secure communication among various entities. We have\u0000utilized the InterPlanetary File System (IPFS) to store encrypted vaccine\u0000passports of citizens securely. Our prototype is built on the Ethereum\u0000platform, with smart contracts deployed on the Sepolia Test network, allowing\u0000for performance evaluation and validation of the system's effectiveness. By\u0000combining IPFS as a distributed data storage platform and Ethereum as a\u0000blockchain platform, our solution paves the way for secure, efficient, and\u0000globally interoperable vaccine passport management, supporting comprehensive\u0000vaccination initiatives worldwide.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"7 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141743475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes an innovative approach to improving quality control of olive oil manufacturing and preventing damage to the machinery caused by foreign objects. We developed a computer-vision-based system that monitors the input of an olive grinder and promptly alerts operators if a foreign object is detected, indicating it by using guided lasers, audio, and visual cues.
{"title":"Collaborative real-time vision-based device for olive oil production monitoring","authors":"Matija Šuković, Igor Jovančević","doi":"arxiv-2407.13285","DOIUrl":"https://doi.org/arxiv-2407.13285","url":null,"abstract":"This paper proposes an innovative approach to improving quality control of\u0000olive oil manufacturing and preventing damage to the machinery caused by\u0000foreign objects. We developed a computer-vision-based system that monitors the\u0000input of an olive grinder and promptly alerts operators if a foreign object is\u0000detected, indicating it by using guided lasers, audio, and visual cues.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"63 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141743472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Malsha Ashani Mahawatta Dona, Beatriz Cabrero-Daniel, Yinan Yu, Christian Berger
Today's advanced driver assistance systems (ADAS), like adaptive cruise control or rear collision warning, are finding broader adoption across vehicle classes. Integrating such advanced, multimodal Large Language Models (LLMs) on board a vehicle, which are capable of processing text, images, audio, and other data types, may have the potential to greatly enhance passenger comfort. Yet, an LLM's hallucinations are still a major challenge to be addressed. In this paper, we systematically assessed potential hallucination detection strategies for such LLMs in the context of object detection in vision-based data on the example of pedestrian detection and localization. We evaluate three hallucination detection strategies applied to two state-of-the-art LLMs, the proprietary GPT-4V and the open LLaVA, on two datasets (Waymo/US and PREPER CITY/Sweden). Our results show that these LLMs can describe a traffic situation to an impressive level of detail but are still challenged for further analysis activities such as object localization. We evaluate and extend hallucination detection approaches when applying these LLMs to video sequences in the example of pedestrian detection. Our experiments show that, at the moment, the state-of-the-art proprietary LLM performs much better than the open LLM. Furthermore, consistency enhancement techniques based on voting, such as the Best-of-Three (BO3) method, do not effectively reduce hallucinations in LLMs that tend to exhibit high false negatives in detecting pedestrians. However, extending the hallucination detection by including information from the past helps to improve results.
{"title":"Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks","authors":"Malsha Ashani Mahawatta Dona, Beatriz Cabrero-Daniel, Yinan Yu, Christian Berger","doi":"arxiv-2408.01433","DOIUrl":"https://doi.org/arxiv-2408.01433","url":null,"abstract":"Today's advanced driver assistance systems (ADAS), like adaptive cruise\u0000control or rear collision warning, are finding broader adoption across vehicle\u0000classes. Integrating such advanced, multimodal Large Language Models (LLMs) on\u0000board a vehicle, which are capable of processing text, images, audio, and other\u0000data types, may have the potential to greatly enhance passenger comfort. Yet,\u0000an LLM's hallucinations are still a major challenge to be addressed. In this\u0000paper, we systematically assessed potential hallucination detection strategies\u0000for such LLMs in the context of object detection in vision-based data on the\u0000example of pedestrian detection and localization. We evaluate three\u0000hallucination detection strategies applied to two state-of-the-art LLMs, the\u0000proprietary GPT-4V and the open LLaVA, on two datasets (Waymo/US and PREPER\u0000CITY/Sweden). Our results show that these LLMs can describe a traffic situation\u0000to an impressive level of detail but are still challenged for further analysis\u0000activities such as object localization. We evaluate and extend hallucination\u0000detection approaches when applying these LLMs to video sequences in the example\u0000of pedestrian detection. Our experiments show that, at the moment, the\u0000state-of-the-art proprietary LLM performs much better than the open LLM.\u0000Furthermore, consistency enhancement techniques based on voting, such as the\u0000Best-of-Three (BO3) method, do not effectively reduce hallucinations in LLMs\u0000that tend to exhibit high false negatives in detecting pedestrians. However,\u0000extending the hallucination detection by including information from the past\u0000helps to improve results.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"47 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141937237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Meiqi Wang, Han Qiu, Longnv Xu, Di Wang, Yuanjie Li, Tianwei Zhang, Jun Liu, Hewu Li
We are witnessing a surge in the use of commercial off-the-shelf (COTS) hardware for cost-effective in-orbit computing, such as deep neural network (DNN) based on-satellite sensor data processing, Earth object detection, and task decision.However, once exposed to harsh space environments, COTS hardware is vulnerable to cosmic radiation and suffers from exhaustive single-event upsets (SEUs) and multi-unit upsets (MCUs), both threatening the functionality and correctness of in-orbit computing.Existing hardware and system software protections against radiation are expensive for resource-constrained COTS nanosatellites and overwhelming for upper-layer applications due to their requirement for heavy resource redundancy and frequent reboots. Instead, we make a case for cost-effective space radiation tolerance using application domain knowledge. Our solution for the on-satellite DNN tasks, name, exploits the uneven SEU/MCU sensitivity across DNN layers and MCUs' spatial correlation for lightweight radiation-tolerant in-orbit AI computing. Our extensive experiments using Chaohu-1 SAR satellite payloads and a hardware-in-the-loop, real data-driven space radiation emulator validate that RedNet can suppress the influence of radiation errors to $approx$ 0 and accelerate the on-satellite DNN inference speed by 8.4%-33.0% at negligible extra costs.
{"title":"A Case for Application-Aware Space Radiation Tolerance in Orbital Computing","authors":"Meiqi Wang, Han Qiu, Longnv Xu, Di Wang, Yuanjie Li, Tianwei Zhang, Jun Liu, Hewu Li","doi":"arxiv-2407.11853","DOIUrl":"https://doi.org/arxiv-2407.11853","url":null,"abstract":"We are witnessing a surge in the use of commercial off-the-shelf (COTS)\u0000hardware for cost-effective in-orbit computing, such as deep neural network\u0000(DNN) based on-satellite sensor data processing, Earth object detection, and\u0000task decision.However, once exposed to harsh space environments, COTS hardware\u0000is vulnerable to cosmic radiation and suffers from exhaustive single-event\u0000upsets (SEUs) and multi-unit upsets (MCUs), both threatening the functionality\u0000and correctness of in-orbit computing.Existing hardware and system software\u0000protections against radiation are expensive for resource-constrained COTS\u0000nanosatellites and overwhelming for upper-layer applications due to their\u0000requirement for heavy resource redundancy and frequent reboots. Instead, we\u0000make a case for cost-effective space radiation tolerance using application\u0000domain knowledge. Our solution for the on-satellite DNN tasks, name, exploits\u0000the uneven SEU/MCU sensitivity across DNN layers and MCUs' spatial correlation\u0000for lightweight radiation-tolerant in-orbit AI computing. Our extensive\u0000experiments using Chaohu-1 SAR satellite payloads and a hardware-in-the-loop,\u0000real data-driven space radiation emulator validate that RedNet can suppress the\u0000influence of radiation errors to $approx$ 0 and accelerate the on-satellite\u0000DNN inference speed by 8.4%-33.0% at negligible extra costs.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"75 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141721524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The advent of blockchain technology and its adoption across various sectors have raised critical discussions about the need for regulatory mechanisms to ensure consumer protection, maintain financial stability, and address privacy concerns without compromising the foundational principles of decentralization and immutability inherent in blockchain platforms. We examine the existing mechanisms for smart contract termination across several major blockchain platforms, including Ethereum, BNB Smart Chain, Cardano, Solana, Hyperledger Fabric, Corda, IOTA, Apotos, and Sui. We assess the compatibility of these mechanisms with the requirements of the EU Data Act, focusing on aspects such as consumer protection, error correction, and regulatory compliance. Our analysis reveals a diverse landscape of approaches, from immutable smart contracts with built-in termination conditions to upgradable smart contracts that allow for post-deployment modifications. We discuss the challenges associated with implementing the so-called smart contract "kill switches," such as the balance between enabling regulatory compliance and preserving the decentralized ethos, the technical feasibility of such mechanisms, and the implications for security and trust in the ecosystem.
{"title":"The Feasibility of a Smart Contract \"Kill Switch\"","authors":"Oshani Seneviratne","doi":"arxiv-2407.10302","DOIUrl":"https://doi.org/arxiv-2407.10302","url":null,"abstract":"The advent of blockchain technology and its adoption across various sectors\u0000have raised critical discussions about the need for regulatory mechanisms to\u0000ensure consumer protection, maintain financial stability, and address privacy\u0000concerns without compromising the foundational principles of decentralization\u0000and immutability inherent in blockchain platforms. We examine the existing\u0000mechanisms for smart contract termination across several major blockchain\u0000platforms, including Ethereum, BNB Smart Chain, Cardano, Solana, Hyperledger\u0000Fabric, Corda, IOTA, Apotos, and Sui. We assess the compatibility of these\u0000mechanisms with the requirements of the EU Data Act, focusing on aspects such\u0000as consumer protection, error correction, and regulatory compliance. Our\u0000analysis reveals a diverse landscape of approaches, from immutable smart\u0000contracts with built-in termination conditions to upgradable smart contracts\u0000that allow for post-deployment modifications. We discuss the challenges\u0000associated with implementing the so-called smart contract \"kill switches,\" such\u0000as the balance between enabling regulatory compliance and preserving the\u0000decentralized ethos, the technical feasibility of such mechanisms, and the\u0000implications for security and trust in the ecosystem.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141721441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The unprecedented growth in the field of machine learning has led to the development of deep neuromorphic networks trained on labelled dataset with capability to mimic or even exceed human capabilities. However, for applications involving continuous decision making in unknown environments, such as rovers for space exploration, robots, unmanned aerial vehicles, etc., explicit supervision and generation of labelled data set is extremely difficult and expensive. Reinforcement learning (RL) allows the agents to take decisions without any (human/external) supervision or training on labelled dataset. However, the conventional implementations of RL on advanced digital CPUs/GPUs incur a significantly large power dissipation owing to their inherent von-Neumann architecture. Although crossbar arrays of emerging non-volatile memories such as resistive (R)RAMs with their innate capability to perform energy-efficient in situ multiply-accumulate operation appear promising for Q-learning-based RL implementations, their limited endurance restricts their application in practical RL systems with overwhelming weight updates. To address this issue and realize the true potential of RRAM-based RL implementations, in this work, for the first time, we perform an algorithm-hardware co-design and propose a novel implementation of Monte Carlo (MC) RL algorithm on passive RRAM crossbar array. We analyse the performance of the proposed MC RL implementation on the classical cart-pole problem and demonstrate that it not only outperforms the prior digital and active 1-Transistor-1-RRAM (1T1R)-based implementations by more than five orders of magnitude in terms of area but is also robust against the spatial and temporal variations and endurance failure of RRAMs.
{"title":"Efficient Reinforcement Learning On Passive RRAM Crossbar Array","authors":"Arjun Tyagi, Shubham Sahay","doi":"arxiv-2407.08242","DOIUrl":"https://doi.org/arxiv-2407.08242","url":null,"abstract":"The unprecedented growth in the field of machine learning has led to the\u0000development of deep neuromorphic networks trained on labelled dataset with\u0000capability to mimic or even exceed human capabilities. However, for\u0000applications involving continuous decision making in unknown environments, such\u0000as rovers for space exploration, robots, unmanned aerial vehicles, etc.,\u0000explicit supervision and generation of labelled data set is extremely difficult\u0000and expensive. Reinforcement learning (RL) allows the agents to take decisions\u0000without any (human/external) supervision or training on labelled dataset.\u0000However, the conventional implementations of RL on advanced digital CPUs/GPUs\u0000incur a significantly large power dissipation owing to their inherent\u0000von-Neumann architecture. Although crossbar arrays of emerging non-volatile\u0000memories such as resistive (R)RAMs with their innate capability to perform\u0000energy-efficient in situ multiply-accumulate operation appear promising for\u0000Q-learning-based RL implementations, their limited endurance restricts their\u0000application in practical RL systems with overwhelming weight updates. To\u0000address this issue and realize the true potential of RRAM-based RL\u0000implementations, in this work, for the first time, we perform an\u0000algorithm-hardware co-design and propose a novel implementation of Monte Carlo\u0000(MC) RL algorithm on passive RRAM crossbar array. We analyse the performance of\u0000the proposed MC RL implementation on the classical cart-pole problem and\u0000demonstrate that it not only outperforms the prior digital and active\u00001-Transistor-1-RRAM (1T1R)-based implementations by more than five orders of\u0000magnitude in terms of area but is also robust against the spatial and temporal\u0000variations and endurance failure of RRAMs.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141611461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
There has been an unprecedented digitization drive in the industrial sector, especially in the maritime industry. The profusion of intelligent electronic devices and IOT-enabled cyber-physical systems (CPS) has helped in the efficient use of resources and increased convenience. CPS has enabled real-time remote command and control of industrial assets. Unlike the relatively isolated legacy systems, the intertwined nature of Information Technology(IT) and Operations Technology(OT) brought by Industry 4.0 has increased the complexity of the systems, thereby increasing the attack surface. This work explores the possible consequences of these attacks from a more holistic view, focusing on high-risk assets such as offshore oil rigs, offshore wind farms, and autonomous vessels. The attacks have become more aggressive with the proliferation of such technologies, disrupting the physical process, causing fire and explosion hazards, and endangering human life and environmental health. The possible attack scenarios, the attack vectors, and their physical consequences have been discussed from the perspective of personnel safety and health, along with known security breaches of such nature. To the best of the authors' knowledge, seldom has any work been done that accentuates the possible human and environmental impacts of such attacks.
{"title":"Cyber Attacks on Maritime Assets and their Impacts on Health and Safety Aboard: A Holistic View","authors":"Mohammad Ammar, Irfan Ahmad Khan","doi":"arxiv-2407.08406","DOIUrl":"https://doi.org/arxiv-2407.08406","url":null,"abstract":"There has been an unprecedented digitization drive in the industrial sector,\u0000especially in the maritime industry. The profusion of intelligent electronic\u0000devices and IOT-enabled cyber-physical systems (CPS) has helped in the\u0000efficient use of resources and increased convenience. CPS has enabled real-time\u0000remote command and control of industrial assets. Unlike the relatively isolated\u0000legacy systems, the intertwined nature of Information Technology(IT) and\u0000Operations Technology(OT) brought by Industry 4.0 has increased the complexity\u0000of the systems, thereby increasing the attack surface. This work explores the\u0000possible consequences of these attacks from a more holistic view, focusing on\u0000high-risk assets such as offshore oil rigs, offshore wind farms, and autonomous\u0000vessels. The attacks have become more aggressive with the proliferation of such\u0000technologies, disrupting the physical process, causing fire and explosion\u0000hazards, and endangering human life and environmental health. The possible\u0000attack scenarios, the attack vectors, and their physical consequences have been\u0000discussed from the perspective of personnel safety and health, along with known\u0000security breaches of such nature. To the best of the authors' knowledge, seldom\u0000has any work been done that accentuates the possible human and environmental\u0000impacts of such attacks.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"63 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141611333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Linh Tran, Sanjay Chari, Md. Saikat Islam Khan, Aaron Zachariah, Stacy Patterson, Oshani Seneviratne
We present the Differentially Private Blockchain-Based Vertical Federal Learning (DP-BBVFL) algorithm that provides verifiability and privacy guarantees for decentralized applications. DP-BBVFL uses a smart contract to aggregate the feature representations, i.e., the embeddings, from clients transparently. We apply local differential privacy to provide privacy for embeddings stored on a blockchain, hence protecting the original data. We provide the first prototype application of differential privacy with blockchain for vertical federated learning. Our experiments with medical data show that DP-BBVFL achieves high accuracy with a tradeoff in training time due to on-chain aggregation. This innovative fusion of differential privacy and blockchain technology in DP-BBVFL could herald a new era of collaborative and trustworthy machine learning applications across several decentralized application domains.
{"title":"A Differentially Private Blockchain-Based Approach for Vertical Federated Learning","authors":"Linh Tran, Sanjay Chari, Md. Saikat Islam Khan, Aaron Zachariah, Stacy Patterson, Oshani Seneviratne","doi":"arxiv-2407.07054","DOIUrl":"https://doi.org/arxiv-2407.07054","url":null,"abstract":"We present the Differentially Private Blockchain-Based Vertical Federal\u0000Learning (DP-BBVFL) algorithm that provides verifiability and privacy\u0000guarantees for decentralized applications. DP-BBVFL uses a smart contract to\u0000aggregate the feature representations, i.e., the embeddings, from clients\u0000transparently. We apply local differential privacy to provide privacy for\u0000embeddings stored on a blockchain, hence protecting the original data. We\u0000provide the first prototype application of differential privacy with blockchain\u0000for vertical federated learning. Our experiments with medical data show that\u0000DP-BBVFL achieves high accuracy with a tradeoff in training time due to\u0000on-chain aggregation. This innovative fusion of differential privacy and\u0000blockchain technology in DP-BBVFL could herald a new era of collaborative and\u0000trustworthy machine learning applications across several decentralized\u0000application domains.","PeriodicalId":501168,"journal":{"name":"arXiv - CS - Emerging Technologies","volume":"47 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141571835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：