Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics最新文献

Curbing Ghost Worker Fraud In Developing Countries Using Consortium Blockchain 利用区块链联盟遏制发展中国家的幽灵工人欺诈

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586569

Musa Ibrahim Bello, Daniel R. Thomas

{"title":"Curbing Ghost Worker Fraud In Developing Countries Using Consortium Blockchain","authors":"Musa Ibrahim Bello, Daniel R. Thomas","doi":"10.1145/3579987.3586569","DOIUrl":"https://doi.org/10.1145/3579987.3586569","url":null,"abstract":"One of the major issues facing the governments of developing countries, such as Nigeria, is ghost worker fraud. Ghost worker fraud refers to all practices relating to employee impersonations that have salary cost effects on the government. More than one hundred billion Naira (220 million US dollars), is lost annually due to ghost workers fraud in Nigeria. Solutions such as the development and implementation of the Integrated Payroll and Personnel Information System (IPPIS) by the Nigerian government did not solve the problem. Blockchain technology offers the promise of improved transparency, auditability, autonomy, security, and efficiency. To address the problem of ghost worker fraud, in this paper, we investigate blockchain and its relevance to ghost workers fraud and other forms of corruption in Nigeria. We also examine the problems of the Integrated Payroll and Personnel Information System (IPPIS). We then propose the use of a consortium blockchain framework to tackle ghost worker fraud and detail the type of consensus algorithm and the blockchain structure required. This framework could substantially reduce cases of ghost worker fraud in Nigeria and elsewhere.","PeriodicalId":327705,"journal":{"name":"Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127906964","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}

引用次数: 0

Deepfake Detection: A Tutorial 深度伪造检测:教程

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586562

M. Rana, A. Sung

引用次数: 0

Continuous Group Key Agreement with Flexible Authorization and Its Applications 具有灵活授权的连续组密钥协议及其应用

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586570

Kaisei Kajita, K. Emura, Kazuto Ogawa, R. Nojima, G. Ohtake

{"title":"Continuous Group Key Agreement with Flexible Authorization and Its Applications","authors":"Kaisei Kajita, K. Emura, Kazuto Ogawa, R. Nojima, G. Ohtake","doi":"10.1145/3579987.3586570","DOIUrl":"https://doi.org/10.1145/3579987.3586570","url":null,"abstract":"Secure messaging (SM) protocols allow users to communicate se-curely over an untrusted infrastructure. Alwen et al. formally de-fined the key agreement protocol used in secure group messaging (SGM) as continuous group key agreement (CGKA) at CRYPTO 2020. In their CGKA protocol, all of the group members have the same rights and a trusted third party is needed. On the other hand, some SGM applications may have a user in the group who has the role of an administrator. When the administrator as the group manager (GM) is distinguished from other group members, i.e., in a one-to-many setting, it would be better for the GM and the other group members to have different authorities. We achieve this flex-ible authorization by incorporating a ratcheting digital signature scheme (Cremers et al. at USENIX Security 2021) into the existing CGKA protocol and demonstrate that such a simple modification allows us to provide flexible authorization. In Alwen et al.'s CGKA protocol, an external public key infrastructure (PKI) functionality as a trusted third party manages the confidential information of users, and the PKI can read all messages until all users update their own keys. In contrast, the GM in our protocol has the same role as the PKI functionality in the group, so no third party outside the group handles confidential information of users and thus no one except group members can read messages regardless of key updates. Our proposed protocol is useful in the creation of new applications such as broadcasting services.","PeriodicalId":327705,"journal":{"name":"Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126258388","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}

引用次数: 1

Disclosure of Multiple "Patient Characteristics" Format Statistics leaks Quasi-identifier Linkage 多个“患者特征”格式统计数据披露泄露准标识符链接

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586571

Kenta Kitamura, Mhd Irvan, Rie Shigetomi Yamaguchi

{"title":"Disclosure of Multiple \"Patient Characteristics\" Format Statistics leaks Quasi-identifier Linkage","authors":"Kenta Kitamura, Mhd Irvan, Rie Shigetomi Yamaguchi","doi":"10.1145/3579987.3586571","DOIUrl":"https://doi.org/10.1145/3579987.3586571","url":null,"abstract":"In recent years, Artificial Intelligence (AI) applications and statistical analysis using big data have become popular. Therefore, regulations for handling personal information have become an issue. However, published statistical information is generally not regulated and is commonly collected and analyzed in many research. In the medical field, \"patient characteristics'', a statistical format of the patients who were the subject of medical research, is included in medical papers. For a single patient characteristics, it is pointed out that its disclosure can lead to anonymity violation, and it is also known that its vulnerability can be quantitatively measured by the Patient Family Detect on Overall Category (PFDOC) entropy. However, the impact of disclosing multiple patient characteristics on anonymity is unknown, particularly in a pandemic where large amounts of statistical information are published for humanitarian purposes. In this paper, we model a pandemic situation and propose a new attack for determining the quasi-identifier (QI) linkage from multiple patient characteristics, which is the premise of a known re-identification attack called the linkage attack. We also introduce a risk indicator called \"N-table contents range confidentiality'' to quantify the confidentiality of the QI linkage. Through theoretical and experimental analysis, we show that to protect the N-table contents range confidentiality, medical institutions should restrict the disclosure of attributes with a population ratio of less than 25% or more than 75%.","PeriodicalId":327705,"journal":{"name":"Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122538476","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}

引用次数: 0

Detecting Online Grooming By Simple Contrastive Chat Embeddings 通过简单的对比聊天嵌入检测在线修饰

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586564

Parisa Rezaee Borj, K. Raja, Patrick A. H. Bours

{"title":"Detecting Online Grooming By Simple Contrastive Chat Embeddings","authors":"Parisa Rezaee Borj, K. Raja, Patrick A. H. Bours","doi":"10.1145/3579987.3586564","DOIUrl":"https://doi.org/10.1145/3579987.3586564","url":null,"abstract":"Protecting children against predators that use the internet as a medium to find their victims is essential, where the difficulty of monitoring online messaging platforms to avoid potential threats toward underage users is alarming. Online grooming detection requires a deep knowledge of predatory behaviour where an online conversation's positive or negative connotations rely on the context where it can change rapidly in an online chat. Therefore, it is essential to use robust feature vectors for predatory conversation detection. This research paper proposes a contrastive learning framework for feature extraction in a sentence-based manner where it can assign a feature vector to the conversation with misspellings using subword information. Also, it is vital to have a high detection rate of true positives to avoid potential non-wanted consequences. We propose a configuration of RoBERTa encoders and supervised SimCSE for training the SVM model, leading to a high rate of detecting relevant samples (predatory samples). Our proposed approach gains an F0.5-score of 0.96, an F1-score of 0.96, and an accuracy of 0.99 for predatory conversation detection that benchmarks the state-of-the-art. In order to improve the performance, we also perform experiments with various fusion approaches, where the sum fusion of all configurations obtains an accuracy of 0.99, an F_1-score of 0.97, and an F0.5-score of 0.98.","PeriodicalId":327705,"journal":{"name":"Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114947486","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}

引用次数: 2

FENet

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586566

{"title":"FENet","authors":"","doi":"10.1145/3579987.3586566","DOIUrl":"https://doi.org/10.1145/3579987.3586566","url":null,"abstract":"Privacy-preserving machine learning (PPML) has been gaining a lot of attention in recent years, and several techniques have been proposed to achieve PPML. Cryptography-based PPML approaches such as Fully Homomorphic Encryption (FHE) and Secure Multiparty Computation (SMC) have been extensively investigated. However, Functional Encryption (FE), which is a newer paradigm, has not been studied as much, and PPML approaches based on FE are in the early stages. Most of the existing FE-based PPML approaches are focused on privacy-preserving inference, and the research work focused on FE-based privacy-preserving training requires a very high training time. To alleviate this issue, this paper presents a privacy-preserving neural network framework using FE that facilitates both training and inference on encrypted data. Our proposed approach is twofold. First, we use Inner-product Functional Encryption (IPFE) and Function-hiding Inner Product Encryption (FHIPE) schemes to develop secure activation functions. To the best of our knowledge, this is the first work to demonstrate the application of FHIPE in PPML. Second, we develop a PPML framework called FENet using the secure activation functions to perform secure forward propagation and backpropagation. Our experimental results show that our framework can successfully train a neural network on the encrypted MNIST dataset with an overall accuracy of 95%. Our work outperforms the state-of-the-art research work in this area, both in terms of reducing the training time by 28× (for IPFE) and 2× (for FHIPE) and improving security.","PeriodicalId":327705,"journal":{"name":"Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122512810","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}

引用次数: 1

Adversarial Robustness of Phishing Email Detection Models 网络钓鱼邮件检测模型的对抗鲁棒性

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586567

Parisa Mehdi Gholampour, Rakesh M. Verma

引用次数: 1

Mitigating Social Media Privacy Concerns - A Comprehensive Study 减轻对社交媒体隐私的担忧——一项综合性研究

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586565

Jeremy McHatton, Kambiz Ghazinour

{"title":"Mitigating Social Media Privacy Concerns - A Comprehensive Study","authors":"Jeremy McHatton, Kambiz Ghazinour","doi":"10.1145/3579987.3586565","DOIUrl":"https://doi.org/10.1145/3579987.3586565","url":null,"abstract":"The growth of social media will not decelerate anytime soon. Un- fortunately, with the growth of new platforms and users, privacy risks are increasing. Many default privacy settings leave new users of social networking sites open and vulnerable to cyberstalking, intelligence gathering, and even identity theft! Thankfully, there are ways to combat these privacy weaknesses through built-in privacy settings. Through review of current articles regarding social media intelligence, privacy settings are found to be adequate, although applying these settings in a successful manner proves to be a monu- mental undertaking. Although, these settings are counter-intuitive and difficult to set up. This is where educational platforms such as Digital-PASS and open-sourced tools such as SocialScore respec- tively can greatly benefit users through gamification or generated reports related to cybersecurity best practices [6]. In fact, it appears that the best methods of preventing such social media intelligence gathering begins with the education of users and the use of third party privacy evaluation tools. This study currently studies the three most common social media in the United States (Facebook, Instagram, Twitter), although future research should be directed towards popular social media sites outside of the U.S. and sites which remain less popular in terms of user traffic. Overall for the three platforms that were studied, Digital-PASS and SocialScore are proven to both practical and applied solutions to the ever growing problem known as social media privacy.","PeriodicalId":327705,"journal":{"name":"Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125838206","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}

引用次数: 0

Privacy-preserving Deep-learning Models for Fingerprint Data using Differential Privacy 基于差分隐私的指纹数据隐私保护深度学习模型

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586568

Maryam Mohammadi, Farida Sabry, Wadha Labda, Q. Malluhi

{"title":"Privacy-preserving Deep-learning Models for Fingerprint Data using Differential Privacy","authors":"Maryam Mohammadi, Farida Sabry, Wadha Labda, Q. Malluhi","doi":"10.1145/3579987.3586568","DOIUrl":"https://doi.org/10.1145/3579987.3586568","url":null,"abstract":"Fingerprint recognition is a widely adopted biometric authentication method that leverages the unique characteristics of fingerprints to identify individuals. Its applications range from access control and authentication to forensic science, making the development of a robust, precise, and secure model for fingerprint recognition and analysis of paramount importance. Recently, deep learning and machine learning models have shown promise in this field, however, the use of these models raises significant privacy concerns as there is a potential for private fingerprint data to be compromised. This research aims to address these concerns by incorporating differential privacy techniques to protect the privacy of fingerprints. It provides evidence that the use of differential privacy technique leads to acceptable trade-off between preserving the privacy of fingerprints and accuracy of fingerprint recognition systems while maintaining robustness against model inversion attacks. With a noise multiplier of 0.01, the verification model attains a good accuracy of 89.32% at privacy budget ε = 1.2 , and less than 80% at lower privacy budget for the identification model.","PeriodicalId":327705,"journal":{"name":"Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132976776","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}

引用次数: 1

Improving Application Artifact Inference Using Matched Sector Adjacency Weighting 利用匹配扇区邻接加权改进应用伪影推断

Proceedings of the 9th ACM International Workshop on Security and Privacy Analytics Pub Date : 2023-04-24 DOI: 10.1145/3579987.3586573

Oluwaseun Adegbehingbe, James H. Jones

引用次数: 0