자료유형 | 학위논문 |
---|---|
서명/저자사항 | Security, Privacy, and Transparency Guarantees for Machine Learning Systems. |
개인저자 | Lecuyer, Mathias. |
단체저자명 | Columbia University. Computer Science. |
발행사항 | [S.l.]: Columbia University., 2019. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
형태사항 | 169 p. |
기본자료 저록 | Dissertations Abstracts International 81-04B. Dissertation Abstract International |
ISBN | 9781088324738 |
학위논문주기 | Thesis (Ph.D.)--Columbia University, 2019. |
일반주기 |
Source: Dissertations Abstracts International, Volume: 81-04, Section: B.
Advisor: Geambasu, Roxana. |
이용제한사항 | This item must not be sold to any third party vendors. |
요약 | Machine learning (ML) is transforming a wide range of applications, promising to bring immense economic and social benefits. However, it also raises substantial security, privacy, and transparency challenges. ML workloads indeed push companies toward aggressive data collection and loose data access policies, placing troves of sensitive user information at risk if the company is hacked. ML also introduces new attack vectors, such as adversarial example attacks, which can completely nullify models' accuracy under attack. Finally, ML models make complex data-driven decisions, which are opaque to the end-users, and difficult to inspect for programmers. In this dissertation we describe three systems we developed. Each system addresses a dimension of the previous challenges, by combining new practical systems techniques with rigorous theory to achieve a guaranteed level of protection, and make systems easier to understand. First we present Sage, a differentially private ML platform that enforces a meaningful protection semantic for the troves of personal information amassed by today's companies. Second we describe PixelDP, a defense against adversarial examples that leverages differential privacy theory to provide a guaranteed level of accuracy under attack. Third we introduce Sunlight, a tool to enhance the transparency of opaque targeting services, using rigorous causal inference theory to explain targeting decisions to end-users. |
일반주제명 | Computer science. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |