Filters








18,951 Hits in 2.8 sec

Adversarial Machine Learning-Industry Perspectives

Ram Shankar Siva Kumar, Magnus Nystrom, John Lambert, Andrew Marshall, Mario Goertzel, Andi Comissoneru, Matt Swann, Sharon Xia
2020 2020 IEEE Security and Privacy Workshops (SPW)  
Based on interviews with 28 organizations, we found that industry practitioners are not equipped with tactical and strategic tools to protect, detect and respond to attacks on their Machine Learning (ML  ...  The goal of this paper is to layout the research agenda to amend the Security Development Lifecycle for industrial-grade software in the adversarial ML era.  ...  the rise of adversarial machine learning.  ... 
doi:10.1109/spw50608.2020.00028 fatcat:s67detoszfdotjo7b2kz3pt4r4

Adversarial Machine Learning – Industry Perspectives [article]

Ram Shankar Siva Kumar, Magnus Nyström, John Lambert, Andrew Marshall, Mario Goertzel, Andi Comissoneru, Matt Swann, Sharon Xia
2021 arXiv   pre-print
Based on interviews with 28 organizations, we found that industry practitioners are not equipped with tactical and strategic tools to protect, detect and respond to attacks on their Machine Learning (ML  ...  We leverage the insights from the interviews and we enumerate the gaps in perspective in securing machine learning systems when viewed in the context of traditional software security development.  ...  the rise of adversarial machine learning.  ... 
arXiv:2002.05646v3 fatcat:i5xgtxpurneo5pxr6nuwvp6vly

Cyber Threat Ontology and Adversarial Machine Learning Attacks: Analysis and Prediction Perturbance

Abel Yeboah-Ofori, Umar Mukhtar Ismail, Tymoteusz Swidurski, Francisca Opoku-Boateng
2021 2021 International Conference on Computing, Computational Modelling and Applications (ICCMA)  
This paper explores the challenges of CTO and adversarial machine learning (AML) attacks for threat prediction to improve cybersecurity. The novelty contributions are threefold.  ...  Machine learning has been used in the cybersecurity domain to predict cyberattack trends.  ...  Cyber Threat and Adversarial Machine Learning C.  ... 
doi:10.1109/iccma53594.2021.00020 fatcat:5ycmd6ysqvb2lmaj3cx35agf7u

Addressing Adversarial Machine Learning Attacks in Smart Healthcare Perspectives [article]

Arawinkumaar Selvakkumar, Shantanu Pal, Zahra Jadidi
2021 arXiv   pre-print
and accuracy of the machine learning model.  ...  In this paper, we address the type of adversarial attacks and their impact on smart healthcare systems. We propose a model to examine how adversarial attacks impact machine learning classifiers.  ...  INTRODUCTION Machine learning has helped multiple industries like healthcare meet their growing demands and exceed expectations in automation [1] .  ... 
arXiv:2112.08862v1 fatcat:pmlut53fordsfmsl4jbdjkhocm

MTS-CycleGAN: An Adversarial-based Deep Mapping Learning Network for Multivariate Time Series Domain Adaptation Applied to the Ironmaking Industry [article]

Cedric Schockaert, Henri Hoyez
2020 arXiv   pre-print
In the current era, an increasing number of machine learning models is generated for the automation of industrial processes.  ...  To elevate machine learning models to a higher level of learning capability, domain adaptation has opened the door for extracting relevant patterns from several assets combined together.  ...  Transfer learning is a key requirement for industry 4.0, in order to scale in the deployment of machine learning models.  ... 
arXiv:2007.07518v1 fatcat:tkxuhbaq6vd3lakb2cvzzkmmgy

Towards quality assurance of software product lines with adversarial configurations

Paul Temple, Mathieu Acher, Gilles Perrouin, Battista Biggio, Jean-Marc Jezequel, Fabio Roli
2019 Proceedings of the 23rd International Systems and Software Product Line Conference - volume A - SPLC '19  
In this paper, we use adversarial ML techniques to generate adversarial configurations fooling ML classifiers and pinpoint incorrect classifications of products (videos) derived from an industrial video  ...  Machine learning (ML) techniques can refine a software product line through learned constraints and a priori prevent non-acceptable products to be derived.  ...  Today, it is called adversarial machine learning and can be seen as a sub-discipline of machine learning.  ... 
doi:10.1145/3336294.3336309 dblp:conf/splc/TempleAPBJR19 fatcat:7ck5kuh7ijbopkklq2fed7pcda

Towards Quality Assurance of Software Product Lines with Adversarial Configurations [article]

Paul Temple, Mathieu Acher, Gilles Perrouin, Battista Biggio, Jean-marc Jezequel, Fabio Roli
2019 arXiv   pre-print
In this paper, we use adversarial ML techniques to generate adversarial configurations fooling ML classifiers and pinpoint incorrect classifications of products (videos) derived from an industrial video  ...  Machine learning (ML) techniques can refine a software product line through learned constraints and a priori prevent non-acceptable products to be derived.  ...  Today, it is called adversarial machine learning and can be seen as a sub-discipline of machine learning.  ... 
arXiv:1909.07283v1 fatcat:lzy75vkrabggbmtmqzb45acypy

Machine Learning for Security and the Internet of Things: the Good, the Bad, and the Ugly

Fan Liang, William G. Hatcher, Weixian Liao, Weichao Gao, Wei Yu
2019 IEEE Access  
More pressing, we consider the vulnerabilities of machine learning (bad use) from the perspectives of security and CPS/IoT, including the ways in which machine learning systems can be compromised, misled  ...  In this paper, we consider the good, the bad, and the ugly use of machine learning for cybersecurity and CPS/IoT.  ...  Considering the challenges outlined above, we now discuss possible future research directions, both from the perspective of advances to machine learning practices and mechanism, as well as the perspective  ... 
doi:10.1109/access.2019.2948912 fatcat:wxd6imn62fgufdmfh3gtaijeru

Security for Machine Learning-based Software Systems: a survey of threats, practices and challenges [article]

Huaming Chen, M. Ali Babar
2022 arXiv   pre-print
In this work, we consider that security for machine learning-based software systems may arise by inherent system defects or external adversarial attacks, and the secure development practices should be  ...  The rapid development of Machine Learning (ML) has demonstrated superior performance in many areas, such as computer vision, video and speech recognition.  ...  When the industry scale MLBSS has now become distributed, a robust distributed machine learning-based system will require Byzantine failure tolerance [13, 104] .  ... 
arXiv:2201.04736v1 fatcat:5g3b2mbapjgelltogqiubv5kda

Fast Authentication and Progressive Authorization in Large-Scale IoT: How to Leverage AI for Security Enhancement? [article]

He Fang, Angie Qi, Xianbin Wang
2019 arXiv   pre-print
and industry processes.  ...  To be more specific, a lightweight intelligent authentication approach is developed by exploring machine learning at the gateway to identify the access time slots or frequencies of resource-constraint  ...  Design of more effective machine learning and distributed machine learning algorithms is also beneficial for the IoT applications and security provisioning.  ... 
arXiv:1907.12092v1 fatcat:g5gyqnz2ibcoplxaek4sckavwu

Machine Learning and Model Checking Join Forces (Dagstuhl Seminar 18121)

Nils Jansen, Joost-Pieter Katoen, Pusmeet Kohli, Jan Kretinsky, Michael Wagner
2018 Dagstuhl Reports  
This Dagstuhl Seminar brought together researchers working in the fields of machine learning and model checking.  ...  This report documents the program and the outcomes of Dagstuhl Seminar 18121 "Machine Learning and Model Checking Join Forces".  ...  This talk aims to provide an overview of government & industry perspectives and cultural challenges with respect to verification & validation of autonomous systems.  ... 
doi:10.4230/dagrep.8.3.74 dblp:journals/dagstuhl-reports/JansenKKK18 fatcat:225qaztsujhgxpclahyf4wm7qe

Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications [article]

Wenjie Ruan and Xinping Yi and Xiaowei Huang
2021 arXiv   pre-print
deep learning models to adversarial examples.  ...  We will also summarize potential research directions concerning the adversarial robustness of deep learning, and its potential benefits to enable accountable and trustworthy deep learning-based data analytical  ...  • Adversarial Machine Learning, in AAAI 2019, AAAI 2018.  ... 
arXiv:2108.10451v1 fatcat:whz2yz2dbbflvmunjej4qknlwi

A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning

Zhiyi Tian, Lei Cui, Jie Liang, Shui Yu
2022 ACM Computing Surveys  
The prosperity of machine learning has been accompanied by increasing attacks on the training process. Among them, poisoning attacks have become an emerging threat during model training.  ...  However, the systematic review from a unified perspective remains blank.  ...  A comprehensive understanding on poisoning attacks will be helpful to guide the academia and industry to develop more robust machine learning methods.  ... 
doi:10.1145/3551636 fatcat:du4jmesfxzfxlkqdaz3rvlqejy

IEEE Intelligent Systems Magazine

2020 Computer  
Siva Kumar et al., Adversar- ial machine learning: Industry perspectives. Feb. , . [Online]. Available: https:arXiv: .  ...  Bonett, "An architectural risk analysis of machine learning systems: Toward more secure ma- chine learning," Berryville Inst. of Machine Learning, San Francisco, . [Online].  ... 
doi:10.1109/mc.2020.2987518 fatcat:zf3ylb2cd5gdnoibsklgvgqfrq

Adversarial attack application analytics in machine learning

Zhang Hongsheng
2022 ITM Web of Conferences  
Machine learning is one of the most widely studied and applied technologies, but it is itself vulnerable to attack and its algorithms have the risk of privacy leakage.  ...  popular speech recognition scene, reveals how to build the antagonism against data, make its differences with the source data is subtle, so much so that humans can't through sensory recognition, and machine  ...  Attackers can interact with machine learning systems as they generate adversarial attack data.  ... 
doi:10.1051/itmconf/20224701005 doaj:ca5dc8e78c684edc8d1f7a1600420879 fatcat:vmazfl5qdng4jmlq3vm44ppy5e
« Previous Showing results 1 — 15 out of 18,951 results