SaTC: CORE: Medium: Understanding and Fortifying Machine Learning Based Security Analytics

SaTC：核心：媒介：理解和强化基于机器学习的安全分析

• 批准号: 1704701
• 负责人: Duen Horng Chau
• 金额: $ 120万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-08-01 至 2021-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1704701&HistoricalAwards=false
• 关键词: SaTC; CORE; Medium; Understanding; Fortifying

Preliminary research has demonstrated that by gaining control of the input data or the computation procedures, attackers can render machine learning based security analysis ineffective. The history of cybersecurity suggests that such attacks will become more prevalent in the real-world soon. This project undertakes the challenge of developing a systematic, foundational, and practical framework to understand attacks, quantify vulnerabilities, and fortify machine learning based security analytics. The framework's effectiveness is evaluated and demonstrated in realistic, user-facing environments, using real malware datasets. This project aims to fundamentally change how machine learning based systems will be designed, developed and deployed for security and malware analytics, cybersecurity more broadly, and numerous other application areas in science, education, and technology, as the use of machine learning is ubiquitous. The findings can lead to new breeds of adaptive defense systems that are highly resilient to current and future security attacks, helping protect the nation and its citizens from cyber harm.This project combines multiple novel ideas synergistically, organized into four inter-related research thrusts: (1) machine learning theoretical framework, based on machine teaching and active learning, for understanding attacks, quantifying vulnerabilities, and measuring the capabilities of adversaries and model robustness; (2) algorithmic techniques for machine learning resilience, to adaptively counter adversaries' feature and sample manipulation strategies; (3) extensive evaluation of the identified attack and defense strategies with real and mutated malware datasets, on existing security systems, and demonstrate the improved attack resilience of the new, fortified machine learning system; (4) system-level countermeasures in real-world user-facing security analysis environments.

初步研究表明，通过控制输入数据或计算过程，攻击者可以使基于机器学习的安全分析无效。网络安全的历史表明，这种攻击很快就会在现实世界中变得更加普遍。该项目承担了开发一个系统的，基础的和实用的框架来理解攻击，量化漏洞，并加强基于机器学习的安全分析的挑战。该框架的有效性进行评估，并在现实的，面向用户的环境中，使用真实的恶意软件数据集证明。该项目旨在从根本上改变基于机器学习的系统的设计，开发和部署方式，以用于安全和恶意软件分析，更广泛的网络安全以及科学，教育和技术中的许多其他应用领域，因为机器学习的使用无处不在。这些发现可能会导致新品种的自适应防御系统，对当前和未来的安全攻击具有高度弹性，有助于保护国家及其公民免受网络伤害。该项目将多种新颖的想法协同结合起来，分为四个相互关联的研究方向：（1）机器学习理论框架，基于机器教学和主动学习，用于理解攻击，量化漏洞，以及测量对手的能力和模型鲁棒性;（2）用于机器学习弹性的算法技术，以自适应地对抗对手的特征和样本操纵策略;（3）在现有的安全系统上利用真实的和突变的恶意软件数据集对所识别的攻击和防御策略进行广泛的评估，并证明新的安全系统的改进的攻击弹性，强化的机器学习系统;（4）现实世界中面向用户的安全分析环境中的系统级对策。

项目成果

Regularizing Neural Networks via Minimizing Hyperspherical Energy

• DOI: 10.1109/cvpr42600.2020.00695
• 发表时间: 2019-06
• 期刊: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Rongmei Lin;Weiyang Liu;Zhen Liu;Chen Feng-;Zhiding Yu;J. Rehg;Li Xiong;Le Song

SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models

SkeletonVis：用于理解人类行为识别模型的对抗性攻击的交互式可视化

• 发表时间: 2021
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Park, Haekyu and

NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions

NeuralDivergence：通过比较激活分布探索和理解神经网络

• 发表时间: 2019
• 期刊: PacificVis 2019
• 作者: Park, Haekyu;Hohman, Fred;Chau, Duen Horng
• 通讯作者: Chau, Duen Horng

NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks

• DOI: 10.1109/tvcg.2021.3114858
• 发表时间: 2021-08
• 期刊: IEEE Transactions on Visualization and Computer Graphics
• 影响因子: 5.2
• 作者: Haekyu Park;Nilaksh Das;Rahul Duggal;Austin P. Wright;Omar Shaikh;Fred Hohman;Duen Horng Chau

Adversarial Attack on Graph Structured Data

• 发表时间: 2018-06
• 作者: H. Dai;Hui Li-;Tian Tian-Tian;Xin Huang;L. Wang;Jun Zhu;Le Song