Adversarial Machine Learning: Attack Surfaces, Defence Mechanisms, Learning Theories in Artificial Intelligence (對抗性機器學習：攻擊面、防禦機制與人工智慧中的學習理論)
Sreevallabh Chivukula, Aneesh, Yang, Xinghao, Liu, Bo
- 出版商: Springer
- 出版日期: 2024-03-07
- 售價: $7,050
- 貴賓價: 9.5 折 $6,698
- 語言: 英文
- 頁數: 302
- 裝訂: Quality Paper - also called trade paper
- ISBN: 303099774X
- ISBN-13: 9783030997748
-
相關分類:
人工智慧、Machine Learning
海外代購書籍(需單獨結帳)
相關主題
商品描述
A critical challenge in deep learning is the vulnerability of deep learning networks to security attacks from intelligent cyber adversaries. Even innocuous perturbations to the training data can be used to manipulate the behaviour of deep networks in unintended ways. In this book, we review the latest developments in adversarial attack technologies in computer vision; natural language processing; and cybersecurity with regard to multidimensional, textual and image data, sequence data, and temporal data. In turn, we assess the robustness properties of deep learning networks to produce a taxonomy of adversarial examples that characterises the security of learning systems using game theoretical adversarial deep learning algorithms. The state-of-the-art in adversarial perturbation-based privacy protection mechanisms is also reviewed.
We propose new adversary types for game theoretical objectives in non-stationary computational learning environments. Proper quantificationof the hypothesis set in the decision problems of our research leads to various functional problems, oracular problems, sampling tasks, and optimization problems. We also address the defence mechanisms currently available for deep learning models deployed in real-world environments. The learning theories used in these defence mechanisms concern data representations, feature manipulations, misclassifications costs, sensitivity landscapes, distributional robustness, and complexity classes of the adversarial deep learning algorithms and their applications.
In closing, we propose future research directions in adversarial deep learning applications for resilient learning system design and review formalized learning assumptions concerning the attack surfaces and robustness characteristics of artificial intelligence applications so as to deconstruct the contemporary adversarial deep learning designs. Given its scope, the book will be of interest to Adversarial Machine Learning practitioners and Adversarial Artificial Intelligence researchers whose work involves the design and application of Adversarial Deep Learning.
商品描述(中文翻譯)
深度學習面臨的一個關鍵挑戰是深度學習網絡對智能網絡對手的安全攻擊的脆弱性。即使是對訓練數據的微小擾動，也可以用來以意想不到的方式操縱深度網絡的行為。在本書中，我們回顧了在計算機視覺、自然語言處理和網絡安全領域中，針對多維、文本和圖像數據、序列數據以及時間數據的對抗攻擊技術的最新發展。接著，我們評估了深度學習網絡的穩健性特徵，以產生一個對抗樣本的分類法，該分類法描述了使用博弈理論對抗深度學習算法的學習系統的安全性。我們還回顧了基於對抗擾動的隱私保護機制的最新技術。
我們為非穩態計算學習環境中的博弈理論目標提出了新的對手類型。在我們研究的決策問題中，對假設集的適當量化導致了各種功能問題、神諭問題、抽樣任務和優化問題。我們還討論了目前可用於在現實環境中部署的深度學習模型的防禦機制。這些防禦機制中使用的學習理論涉及數據表示、特徵操作、錯誤分類成本、敏感性景觀、分佈穩健性以及對抗深度學習算法的複雜性類別及其應用。
最後，我們提出了對抗深度學習應用的未來研究方向，以設計具有韌性的學習系統，並回顧了有關攻擊面和人工智慧應用的穩健性特徵的正式學習假設，以解構當代的對抗深度學習設計。考慮到本書的範疇，將對從事對抗機器學習和對抗人工智慧研究的實踐者和研究人員感興趣，他們的工作涉及對抗深度學習的設計和應用。
作者簡介
Dr. Aneesh Sreevallabh Chivukula is currently an Assistant Professor in the Department of Computer Science & Information Systems at the Birla Institute of Technology and Science (BITS), Pilani, Hyderabad Campus. He has a PhD in data analytics and machine learning from the University of Technology Sydney (UTS), Australia. He holds a Master Of Science by Research in computer science and artificial intelligence from the International Institute of Information Technology Hyderabad, India. His research interests are in Computational Algorithms, Adversarial Learning, Machine Learning, Deep Learning, Data Mining, Game Theory, and Robust Optimization. He has taught subjects on advanced analytics and problem solving at UTS. He has been teaching academic courses on computer science at BITS, Pilani. He has industry experience in engineering, R&D, consulting at research labs and startup companies. Hehas developed enterprise solutions across the value chains in the open source, Cloud, & Big Data markets.
Dr. Xinghao Yang is currently an Associate Professor at the China University of Petroleum. He has a Ph.D. degree in advanced analytics from the University of Technology Sydney, Sydney, NSW, Australia. His research interests include multiview learning and adversarial machine learning with publications on information fusion and information sciences.
Dr. Wei Liu is the Director of Future Intelligence Research Lab, and an Associate Professor in Machine Learning, in the School of Computer Science, the University of Technology Sydney (UTS), Australia. He is a core member of the UTS Data Science Institute. Wei obtained his PhD degree in Machine Learning research at the University of Sydney (USyd). His current research focuses are adversarial machine learning, game theory, causal inference, multimodal learning, and natural language processing. Wei's research papers are constantly published in CORE A*/A and Q1 (i.e., top-prestigious) journals and conferences. He has received 3 Best Paper Awards. Besides, one of his first-authored papers received the Most Influential Paper Award in the CORE A Ranking conference PAKDD 2021. He was a nominee for the Australian NSW Premier's Prizes for Early Career Researcher Award in 2017. He has obtained more than $2 million government competitive and industry research funding in the past six years.
Dr. Bo Liu is currently a Senior Lecturer with the University of Technology Sydney, Australia. His research interests include cybersecurity and privacy, location privacy and image privacy, privacy protection and machine learning, wireless communications and networks. He is an IEEE Senior Member and Associate Editor of IEEE Transactions on Broadcasting.
Dr. Wanlei Zhou received the Ph.D. degree from Australian National University, Canberra, ACT, Australia, in 1991, all in computer science and engineering, and the D.Sc. degree from Deakin University, Melbourne, VIC, Australia, in 2002. He is currently a Professor and the Head of School of Computer Science at the University of Technology Sydney. He served as a Lecturer with the University of Electronic Science and Technology of China, a System Programmer with Hewlett Packard, Boston, MA, USA, and a Lecturer with Monash University, Melbourne, VIC, Australia, and the National University of Singapore, Singapore. He has published over 300 papers in refereed international journals and refereed international conferences proceedings. His research interests include distributed systems, network security, bioinformatics, and e-Learning. Dr. Wanlei was the General Chair/Program Committee Chair/Co-Chair of a number of international conferences, including ICA3PP, ICWL, PRDC, NSS, ICPAD, ICEUC, and HPCC.
作者簡介(中文翻譯)
Dr. Aneesh Sreevallabh Chivukula 目前是比爾拉科技與科學學院（BITS）海得拉巴校區計算機科學與資訊系的助理教授。他擁有澳大利亞悉尼科技大學（UTS）數據分析和機器學習的博士學位，並在印度海得拉巴國際資訊技術學院獲得計算機科學和人工智慧的研究碩士學位。他的研究興趣包括計算算法、對抗學習、機器學習、深度學習、數據挖掘、博弈論和穩健優化。他曾在UTS教授高級分析和問題解決的課程，並在BITS, Pilani教授計算機科學的學術課程。他在工程、研發、研究實驗室和初創公司的諮詢方面擁有行業經驗，並在開源、雲端和大數據市場開發企業解決方案。
Dr. Xinghao Yang 目前是中國石油大學的副教授。他擁有澳大利亞悉尼科技大學的高級分析博士學位。他的研究興趣包括多視角學習和對抗機器學習，並在信息融合和信息科學方面發表了相關論文。
Dr. Wei Liu 是未來智能研究實驗室的主任，並在澳大利亞悉尼科技大學（UTS）計算機科學學院擔任機器學習副教授。他是UTS數據科學研究所的核心成員。Wei 在悉尼大學（USyd）獲得機器學習研究的博士學位。他目前的研究重點包括對抗機器學習、博弈論、因果推斷、多模態學習和自然語言處理。Wei 的研究論文不斷發表在CORE A*/A和Q1（即頂尖）期刊和會議上，並獲得了三項最佳論文獎。此外，他的一篇第一作者論文在CORE A排名的會議PAKDD 2021中獲得了最具影響力論文獎。他在2017年被提名為澳大利亞新南威爾士州總理早期職業研究者獎。過去六年，他獲得了超過200萬美元的政府競爭性和行業研究資金。
Dr. Bo Liu 目前是澳大利亞悉尼科技大學的高級講師。他的研究興趣包括網絡安全和隱私、位置隱私和圖像隱私、隱私保護和機器學習、無線通信和網絡。他是IEEE的高級會員，並擔任IEEE廣播期刊的副編輯。
Dr. Wanlei Zhou 於1991年在澳大利亞國立大學獲得計算機科學與工程的博士學位，並於2002年在澳大利亞迪肯大學獲得科學博士學位。他目前是澳大利亞悉尼科技大學計算機科學學院的教授及院長。他曾在中國電子科技大學擔任講師，在美國惠普公司擔任系統程式設計師，並在澳大利亞莫納什大學和新加坡國立大學擔任講師。他在國際期刊和國際會議論文集中發表了300多篇論文。他的研究興趣包括分散式系統、網絡安全、生物信息學和電子學習。Dr. Wanlei 曾擔任多個國際會議的總主席/程序委員會主席/聯合主席，包括ICA3PP、ICWL、PRDC、NSS、ICPAD、ICEUC和HPCC。
