T
Tudor Dumitras
Researcher at University of Maryland, College Park
Publications - 96
Citations - 3977
Tudor Dumitras is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Malware & Fault tolerance. The author has an hindex of 29, co-authored 96 publications receiving 3369 citations. Previous affiliations of Tudor Dumitras include Carnegie Mellon University & Symantec.
Papers
More filters
Proceedings ArticleDOI
Before we knew it: an empirical study of zero-day attacks in the real world
Leyla Bilge,Tudor Dumitras +1 more
TL;DR: This paper describes a method for automatically identifying zero-day attacks from field-gathered data that records when benign and malicious binaries are downloaded on 11 million real hosts around the world and identifies 18 vulnerabilities exploited before disclosure.
Proceedings Article
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
Ali Shafahi,W. Ronny Huang,Mahyar Najibi,Octavian Suciu,Christoph Studer,Tudor Dumitras,Tom Goldstein +6 more
TL;DR: This paper explores poisoning attacks on neural nets using "clean-labels", an optimization-based method for crafting poisons, and shows that just one single poison image can control classifier behavior when transfer learning is used.
Posted Content
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
Ali Shafahi,W. Ronny Huang,Mahyar Najibi,Octavian Suciu,Christoph Studer,Tudor Dumitras,Tom Goldstein +6 more
TL;DR: In this article, the authors present an optimization-based method for crafting poisons, and show that just one single poison image can control classifier behavior when transfer learning is used, and demonstrate their method by generating poisoned frog images from CIFAR dataset and using them to manipulate image classifiers.
Proceedings Article
Vulnerability disclosure in the age of social media: exploiting twitter for predicting real-world exploits
TL;DR: A quantitative and qualitative exploration of the vulnerability-related information disseminated on Twitter is conducted, the design of a Twitter-based exploit detector is described, and a threat model specific to the problem is introduced.
Proceedings Article
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
TL;DR: The Shallow-Deep Network (SDN) is proposed, a generic modification to off-the-shelf DNNs that introduces internal classifiers that can mitigate the wasteful effect of overthinking with confidence-based early exits and reduce the average inference cost by more than 50% and preserve the accuracy.