Sanghyun Hong
Sanghyun Hong
PhD Candidate in Computer Science, University of Maryland, College Park
Email verificata su - Home page
Citata da
Citata da
Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks
S Hong, P Frigo, Y Kaya, C Giuffrida, T Dumitraş
28th USENIX Security Symposium (USENIX Security 19). Santa Clara, CA: USENIX …, 2019
Shallow-deep networks: Understanding and mitigating network overthinking
Y Kaya, S Hong, T Dumitras
International Conference on Machine Learning, 3301-3310, 2019
Security analysis of deep neural networks operating in the presence of cache side-channel attacks
S Hong, M Davinroy, Y Kaya, SN Locke, I Rackow, K Kulda, ...
arXiv preprint arXiv:1810.03487, 2018
Summoning demons: The pursuit of exploitable bugs in machine learning
R Stevens, O Suciu, A Ruef, S Hong, M Hicks, T Dumitraş
arXiv preprint arXiv:1701.04739, 2017
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
S Hong, V Chandrasekaran, Y Kaya, T Dumitraş, N Papernot
arXiv preprint arXiv:2002.11497, 2020
Go serverless: securing cloud via serverless design patterns
S Hong, A Srivastava, W Shambrook, T Dumitraș
10th {USENIX} Workshop on Hot Topics in Cloud Computing (HotCloud 18), 2018
SENA: preserving social structure for network embedding
S Hong, T Chakraborty, S Ahn, G Husari, N Park
Proceedings of the 28th ACM Conference on Hypertext and Social Media, 235-244, 2017
How to 0wn NAS in Your Spare Time
S Hong, M Davinroy, Y Kaya, D Dachman-Soled, T Dumitraş
8th International Conference on Learning Representations (ICLR 2020)., 2020
Page: Answering graph pattern queries via knowledge graph embedding
S Hong, N Park, T Chakraborty, H Kang, S Kwon
International Conference on Big Data, 87-99, 2018
Peek-a-boo: Inferring program behaviors in a virtualized infrastructure without introspection
S Hong, A Nicolae, A Srivastava, T Dumitraş
Computers & Security 79, 190-207, 2018
On integrating knowledge graph embedding into sparql query processing
H Kang, S Hong, K Lee, N Park, S Kwon
2018 IEEE International Conference on Web Services (ICWS), 371-374, 2018
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
S Hong, Y Kaya, IV Modoranu, T Dumitraş
arXiv preprint arXiv:2010.02432, 2020
On the Effectiveness of Regularization Against Membership Inference Attacks
Y Kaya, S Hong, T Dumitras
arXiv preprint arXiv:2006.05336, 2020
Poster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset
S Hong, T Kim, T Dumitraş, J Choi
The Network and Distributed System Security Symposium (NDSS) 2019, 2019
Fatty and Skinny: A Joint Training Method of Watermark Encoder and Decoder
S Hong, M Mohammadi, N Park
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–15