D
Dawn Song
Researcher at University of California, Berkeley
Publications - 504
Citations - 75245
Dawn Song is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 117, co-authored 460 publications receiving 61572 citations. Previous affiliations of Dawn Song include FireEye, Inc. & University of California.
Papers
More filters
Posted Content
Aligning AI With Shared Human Values
TL;DR: With the ETHICS dataset, it is found that current language models have a promising but incomplete understanding of basic ethical knowledge, and it provides a steppingstone toward AI that is aligned with human values.
Proceedings ArticleDOI
Mining Permission Request Patterns from Android and Facebook Applications
TL;DR: In this paper, the authors cluster a corpus of 188,389 Android applications and 27,029 Face book applications to find patterns in permission requests, and find that Face book permission requests follow a clear structure that can be fitted well with only five patterns, whereas Android applications demonstrate more complex permission requests.
Proceedings Article
Towards Efficient Data Valuation Based on the Shapley Value
Ruoxi Jia,David Dao,Boxin Wang,Frances Ann Hubis,Nicholas Hynes,Nezihe Merve Gürel,Bo Li,Ce Zhang,Dawn Song,Costas J. Spanos +9 more
TL;DR: In this article, the authors study the problem of ''how much is my data worth'' by utilizing the Shapley value, a popular notion of value which originated in co-operative game theory.
Book ChapterDOI
Behavioral distance measurement using hidden markov models
TL;DR: In this paper, the authors proposed a new approach to behavioral distance calculation using a new type of Hidden Markov Model, and empirically evaluated the intrusion detection capability of their proposal when used to measure the distance between the system call behaviors of diverse web servers.
Proceedings Article
Robust anomaly detection and backdoor attack detection via differential privacy
Min Du,Ruoxi Jia,Dawn Song +2 more
TL;DR: It is demonstrated that applying differential privacy can improve the utility of outlier detection and novelty detection, with an extension to detect poisoning samples in backdoor attacks.