Zobrazeno 1 - 10
of 197
pro vyhledávání: '"Gunter, Carl A."'
Graph Neural Networks (GNNs) have been widely applied to different tasks such as bioinformatics, drug design, and social networks. However, recent studies have shown that GNNs are vulnerable to adversarial attacks which aim to mislead the node or sub
Externí odkaz:
http://arxiv.org/abs/2212.13607
The number of IoT devices in smart homes is increasing. This broad adoption facilitates users' lives, but it also brings problems. One such issue is that some IoT devices may invade users' privacy. Some reasons for this invasion can stem from obscure
Externí odkaz:
http://arxiv.org/abs/2210.06676
Autor:
Nahrstedt, Klara, Shanbhag, Naresh, Adve, Vikram, Amato, Nancy, Choudhury, Romit Roy, Gunter, Carl, Kim, Nam Sung, Milenkovic, Olgica, Mitra, Sayan, Varshney, Lav, Vlasov, Yurii, Adve, Sarita, Bashir, Rashid, Cangellaris, Andreas, DiCarlo, James, Driggs-Campbell, Katie, Feamster, Nick, Gazzola, Mattia, Karahalios, Karrie, Koyejo, Sanmi, Kwiat, Paul, Li, Bo, Mehr, Negar, Mehra, Ravish, Miller, Andrew, Rus, Daniela, Schwing, Alex, Shrivastava, Anshumali
In 2021, the Coordinated Science Laboratory CSL, an Interdisciplinary Research Unit at the University of Illinois Urbana-Champaign, hosted the Future of Computing Symposium to celebrate its 70th anniversary. CSL's research covers the full computing s
Externí odkaz:
http://arxiv.org/abs/2210.08974
Autor:
Gunter, George, Li, Huichen, Hojjati, Avesta, Nice, Matthew, Bunting, Matthew, Gunter, Carl A., Li, Bo, Sprinkle, Jonathan, Work, Daniel
We demonstrate that a supply-chain level compromise of the adaptive cruise control (ACC) capability on equipped vehicles can be used to significantly degrade system level performance of current day mixed-autonomy freeway networks. Via a simple threat
Externí odkaz:
http://arxiv.org/abs/2112.11986
Users can improve the security of remote communications by using Trusted Execution Environments (TEEs) to protect against direct introspection and tampering of sensitive data. This can even be done with applications coded in high-level languages with
Externí odkaz:
http://arxiv.org/abs/2102.05195
Autor:
Huang, Hsiao-Ying, Demetriou, Soteris, Banerjee, Rini, Tuncay, Güliz Seray, Gunter, Carl A., Bashir, Masooda
Despite widespread use of smartphones, there is no measurement standard targeted at smartphone security behaviors. In this paper we translate a well-known cybersecurity behavioral scale into the smartphone domain and show that we can improve on this
Externí odkaz:
http://arxiv.org/abs/2007.01721
Autor:
Burleson, Wayne, Fu, Kevin, Anthony, Denise, Guajardo, Jorge, Gunter, Carl, Ingols, Kyle, Jeannin, Jean-Baptiste, Koushanafar, Farinaz, Landwehr, Carl, Squires, Susan
Protecting embedded security is becoming an increasingly challenging research problem for embedded systems due to a number of emerging trends in hardware, software, networks, and applications. Without fundamental advances in, and an understanding of
Externí odkaz:
http://arxiv.org/abs/2005.06585
In machine learning Trojan attacks, an adversary trains a corrupted model that obtains good performance on normal data but behaves maliciously on data samples with certain trigger patterns. Several approaches have been proposed to detect such attacks
Externí odkaz:
http://arxiv.org/abs/1910.03137
Web services offer an opportunity to redesign a variety of older systems to exploit the advantages of a flexible, extensible, secure set of standards. In this work we revisit WSEmail, a system proposed over ten years ago to improve email by redesigni
Externí odkaz:
http://arxiv.org/abs/1908.02108
Autor:
Long, Yunhui, Wang, Boxin, Yang, Zhuolin, Kailkhura, Bhavya, Zhang, Aston, Gunter, Carl A., Li, Bo
Recent advances in machine learning have largely benefited from the massive accessible training data. However, large-scale data sharing has raised great privacy concerns. In this work, we propose a novel privacy-preserving data Generative model based
Externí odkaz:
http://arxiv.org/abs/1906.09338