Filters








1,848 Hits in 4.7 sec

Less is More: A privacy-respecting Android malware classifier using Federated Learning [article]

Rafa Gálvez, Veelasha Moonsamy, Claudia Diaz
2021 arXiv   pre-print
In this paper we present LiM ("Less is More"), a malware classification framework that leverages Federated Learning to detect and classify malicious apps in a privacy-respecting manner.  ...  We implement LiM and show that the cloud server has F1 score of 95%, while clients have perfect recall with only 1 false positive in >100 apps, using a dataset of 25K clean apps and 25K malicious apps,  ...  Acknowledgements We also thank Brecht Van der Vliet for his helpful review of the code and the identification of an important implementation issue.  ... 
arXiv:2007.08319v3 fatcat:dc2xrh5srvewdbzv224p5y6qjy

Less is More: A privacy-respecting Android malware classifier using federated learning

Rafa Gálvez, Veelasha Moonsamy, Claudia Diaz
2021 Proceedings on Privacy Enhancing Technologies  
In this paper we present LiM ('Less is More'), a malware classification framework that leverages Federated Learning to detect and classify malicious apps in a privacy-respecting manner.  ...  We implement LiM and show that the cloud server has F1 score of 95%, while clients have perfect recall with only 1 false positive in > 100 apps, using a dataset of 25K clean apps and 25K malicious apps  ...  Acknowledgements We also thank Brecht Van der Vliet for his helpful review of the code and the identification of an important implementation issue.  ... 
doi:10.2478/popets-2021-0062 fatcat:s3abkiawdjfd3i6c4cgzipnn6m

Stackelberg Security Game For Optimizing Security Of Federated Internet Of Things Platform Instances

Violeta Damjanovic-Behrendt
2017 Zenodo  
This paper presents an approach for optimal cyber security decisions to protect instances of a federated Internet of Things (IoT) platform in the cloud.  ...  The proposed security optimization components will be validated in a collaborative cloud platform that is based on the Industrial Internet Reference Architecture (IIRA) and its recently published security  ...  a federated platform, residing in the cloud.  ... 
doi:10.5281/zenodo.1130143 fatcat:ioupac6cbvaz3lftjcptnz5aru

Federated Learning for 6G Communications: Challenges, Methods, and Future Directions [article]

Yi Liu, Xingliang Yuan, Zehui Xiong, Jiawen Kang, Xiaofei Wang, Dusit Niyato
2020 arXiv   pre-print
In this article, we first introduce the integration of 6G and federated learning and provide potential federated learning applications for 6G.  ...  We then describe key technical challenges, the corresponding federated learning methods, and open problems for future research on federated learning in the context of 6G communications.  ...  Liu et al. in [9] utilized the smart contract techniques in the blockchain to design a malicious device detection mechanism to alleviate the malicious attack problems. 3) Reliable Reputation Management  ... 
arXiv:2006.02931v2 fatcat:df3bzirq2fcpnp7h3kagdgamiy

Enhancing Privacy via Hierarchical Federated Learning [article]

Aidmar Wainakh, Alejandro Sanchez Guinea, Tim Grube, Max Mühlhäuser
2020 arXiv   pre-print
In this paper, we discuss applying federated learning on a hierarchical architecture as a potential solution.  ...  A number of these issues are aggravated by the centralized architecture of federated learning.  ...  We can observe this advantage in the organizational structure of companies [9] . FL was originally proposed with the intention to be based on a cloud computing infrastructure [17] .  ... 
arXiv:2004.11361v1 fatcat:cntbwwn3ovgqfaejt727dzcw4a

FLEAM: A Federated Learning Empowered Architecture to Mitigate DDoS in Industrial IoT [article]

J. Li, L. Lyu, X. Liu, X. Zhang, X. Lyu
2021 arXiv   pre-print
Current centralized mitigation solutions concentrate on detection and mitigation at a victim's side, paying inadequate attention to hacking costs and the collaboration of defenders.  ...  The distributed denial of service (DDoS) attack is detrimental to the industrial Internet of things (IIoT) as it triggers severe resource starvation on networked objects.  ...  Grounded in federated learning (FL), our FLEAM only needs to upload model parameters to the cloud aggregator.  ... 
arXiv:2012.06150v2 fatcat:jzfv2jxglje7bcsddqep6tem5m

STRATUS: Towards Returning Data Control to Cloud Users [chapter]

Ryan K. L. Ko, Giovanni Russello, Richard Nelson, Shaoning Pang, Aloysius Cheang, Gill Dobbie, Abdolhossein Sarrafzadeh, Sivadon Chaisiri, Muhammad Rizwan Asghar, Geoffrey Holmes
2015 Lecture Notes in Computer Science  
Exposing the data at some point in the cloud to a few privileged users is undoubtedly a vendorcentric approach, and hinges on the trust relationships data owners have with their cloud service providers  ...  and User-centric Services in the Cloud) research project.  ...  Acknowledgements This research is supported by STRATUS (Security Technologies Returning Accountability, Trust and User-Centric Services in the Cloud) (https://stratus.org.nz), a science investment project  ... 
doi:10.1007/978-3-319-27161-3_6 fatcat:mberng3n2zhslmosqcqf3nraau

CloRoFor: Cloud Robust Forensics [article]

Roberto Battistoni, Roberto Di Pietro, Flavio Lombardi
2015 arXiv   pre-print
The malicious alteration of machine time is a big challenge in computer forensics. Detecting such changes and reconstructing the actual timeline of events is of paramount importance.  ...  In this paper we survey the issues related to host and guest machine time integrity in the cloud.  ...  on the cloud by cloud and service providers and, by service users.  ... 
arXiv:1506.01739v1 fatcat:ngmqv5qztbgyllzm4jtdmika4u

Editorial: Security and Privacy Protection for Mobile Applications and Platforms

Victor Sucasas, Georgios Mantas, Saud Althunibat, José-Fernán Martínez Ortega
2020 Journal on spesial topics in mobile networks and applications  
The first article, "Reliable Data Analysis through Blockchain based Crowdsourcing in Mobile Ad-hoc Cloud", authored by Saqib Rasool, proposed a blockchain based reputation system for detection of malicious  ...  analysis for the detection of malicious software in mobile devices, and caters for its Android implementation.  ... 
doi:10.1007/s11036-019-01438-w fatcat:wvhaspvsbjc6vkf7i75rst75dy

Exploration of Vulnerabilities, Threats and Forensic Issues and its impact on the Distributed Environment of Cloud and its mitigation

Gayatri S Pandi (Jain), Saurabh Shah, K.H. Wandra
2020 Procedia Computer Science  
Evidence collection and analysis in the digital world and especially in cloud environment is a great challenge. This paper also touches on a few issues of forensics in cloud computing environment.  ...  Evidence collection and analysis in the digital world and especially in cloud environment is a great challenge. This paper also touches on a few issues of forensics in cloud computing environment.  ...  The authors are also thankful to the staff members of LJK trust, Dr. H.B.Bhadka of C.U.Shah University, Dr. Sameer Patel of PDP University, Dr.  ... 
doi:10.1016/j.procs.2020.03.194 fatcat:hy7dsllia5c5biq24xlfhdihwm

A Hybrid Model is Proposed Based in The Combination of Genetic and MAFS in Cloud Environment

V. Chinnasamy, D. Maruthanayagam
2018 International Journal of Scientific Research in Computer Science Engineering and Information Technology  
The objective of this paper is to suggest new security mechanisms using various trust approaches in broker based federated cloud architecture, ranking the providers with the help of regression tree approach  ...  Data security has a major issue in cloud computing environment; An intrusion detection system (IDS) is a component that helps to detect various types of malicious network traffic which cannot be detected  ...  The type of action triggered when a malicious behavior is detected, an IDS can be active or passive: (a) Passive IDS: when a malicious behavior is detected, an alert is raised and no further action is  ... 
doi:10.32628/cseit183887 fatcat:7xgiczr6zrcf7o7hfdhmuqoyri

A survey on security issues and solutions at different layers of Cloud computing

Chirag Modi, Dhiren Patel, Bhavesh Borisaniya, Avi Patel, Muttukrishnan Rajarajan
2012 Journal of Supercomputing  
This is the accepted version of the paper. This version of the publication may differ from the final published version.  ...  Abstract Cloud computing offers scalable on-demand services toconsumers with greater flexibility and lesser infrastructure investment.  ...  Research is still needed to detect EDoS attacks in the Cloud. F. Y.  ... 
doi:10.1007/s11227-012-0831-5 fatcat:mj7kwrsbqnedhjbw72wbtjwfve

A Critique of Active Defense or 'Hack Back'

Anthony Caldwell, Kevin Curran
2020 International Journal for Information Security Research  
federal laws.  ...  Beyond the context of "ethical hacking" where network attacks are conducted with the explicit permission of the network owner, such as during a penetration test, "hacking" typically violates state and  ...  Instead of facing an infrastructure based on separate physical boxes, an attacker can now purchase a cloud node from the same provider as used by the organisation they wish to compromise, the malicious  ... 
doi:10.20533/ijisr.2042.4639.2020.0109 fatcat:opsbc72govfz7a3uf2ffewytra

Landmark-based data location verification in the cloud: review of approaches and challenges

Malik Irain, Jacques Jorda, Zoubir Mammeri
2017 Journal of Cloud Computing: Advances, Systems and Applications  
Data storage on the cloud is growing every day and many companies, administrations, and individuals are now outsourcing storage of their data to large-scale Cloud Service Providers (CSP).  ...  The objective of this paper is twofold: propose a comprehensive classification of the location verification approaches and discuss their vulnerabilities regarding malicious CSP attacks.  ...  violating a data storage law, which stipulates the personal data of Russian users must be stored on the territory of the Russian Federation [12] .  ... 
doi:10.1186/s13677-017-0095-y fatcat:h5dav7modfc25erz6n37pssm3y

Deconstructing the Decentralization Trilemma

Harry Halpin
2020 Proceedings of the 17th International Joint Conference on e-Business and Telecommunications  
The vast majority of applications at this moment rely on centralized servers to relay messages between clients, where these servers are considered trusted third-parties.  ...  With the rise of blockchain technologies over the last few years, there has been a move away from both centralized servers and traditional federated models to more decentralized peer-to-peer alternatives  ...  Rather than a binary division, we view decentralization on a spectrum that can be broadly construed as centralized, federated, and decentralized architectures in Section 4, and we provide an analysis in  ... 
doi:10.5220/0009892405050512 dblp:conf/icete/Halpin20 fatcat:fylsc3wvwjcxfklsmtrlhmjmyi
« Previous Showing results 1 — 15 out of 1,848 results