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
Data Poisoning Attack against Unsupervised Node Embedding Methods
TL;DR: A complete characterization of attacker's utilities is given and efficient solutions to adversarial attacks for two popular node embedding methods: DeepWalk and LINE are presented.
Proceedings Article
Privilege separation in HTML5 applications
TL;DR: A new design for achieving effective privilege separation in HTML5 applications that shows how applications can cheaply create arbitrary number of components and considerably improves auditability is proposed.
ReportDOI
Private and threshold set-intersection
Lea Kissner,Dawn Song +1 more
TL;DR: This paper considers the problem of privately computing the intersection of sets (set-intersection), as well as several variations on this problem: cardinality set-intersections, threshold set- Intersection, and over-threshold set-Intersection.
Book ChapterDOI
Malware analysis with tree automata inference
TL;DR: An algorithm for inferring k-testable tree automata from system call dataflow dependency graphs and the use of inferred automata in malware recognition and classification is developed.
Proceedings ArticleDOI
REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data
TL;DR: The experimental results demonstrate that fine-tuning based watermark removal attacks could pose real threats to the copyright of pre-trained models, and highlight the importance of further investigating the watermarking problem and proposing more robust watermark embedding schemes against the attacks.