Sort by: |

Color Palettes: Conferences and Journals | Workshops | Posters | Preprints
2019
Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks.

Sanghyun Hong, Pietro Frigo, Yigitcan Kaya, Cristiano Giuffrida, and Tudor Dumitraș.
USENIX Security Symposium, 2019 (USENIX).
Paper Presentation

Shallow-Deep Networks: Understanding and Mitigating Network Overthinking.

Yigitcan Kaya, Sanghyun Hong, and Tudor Dumitraș.
International Conference on Machine Learning, 2019 (ICML).
Paper Presentation Poster Code Website

Poster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset

Sanghyun Hong, Tae-hoon Kim, Tudor Dumitraş, Jonghyun Choi
The Network and Distributed System Security Symposium, 2019 (NDSS).
Paper Poster

2018
Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks

*Sanghyun Hong, *Michael Davinroy, Yiǧitcan Kaya, Stuart Nevans Locke, Ian Rackow, Kevin Kulda, Dana Dachman-Soled, Tudor Dumitraş (* indicates equal contribution)
arXiv Preprint, 2018 (arXiv).
Paper Code

Peek-a-Boo: Inferring Program Behaviors in a Virtualized Infrastructure without Introspections.

Sanghyun Hong, Alina Nicolae, Abhinav Srivastava, and Tudor Dumitraș.
Computer & Security, 2018 (COSE).
Paper

Go Serverless: Securing Cloud via Serverless Design Patterns.

Sanghyun Hong, Abhinav Srivastava, William Shambrook, and Tudor Dumitraș.
USENIX Workshop on Hot Topics in Cloud Computing, 2018 (HotCloud 18).
Paper Presentation

PAGE: Answering Graph Pattern Queries via Knowledge Graph Embedding.

Sanghyun Hong, Noseong Park, Tanmoy Chakraborty, Hyunjoong Kang, Soonhyun Kwon.
International Conference on Big Data, 2018 (BigData).
Paper Presentation

On Integrating Knowledge Graph Embedding into SPARQL Query Processing.

Soonhyun Kwon Hyunjoong Kang, Sanghyun Hong, Kookjin Lee, Noseong Park.
International Conference on Web Services, 2018. (ICWS) [Work in Progress Papers]
Paper

2017
SENA: Preserving Social Structure for Network Embedding.

*Sanghyun Hong, *Tanmoy Chakraborty, Sungjin Ahn, Ghaith Husari, Noseong Park. (* indicates equal contribution)
ACM Conference on Hypertext and Social Media, 2017 (ACM HT).
Paper

2016
Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning.

Rock Stevens, Octavian Suciu, Andrew Ruef, Sanghyun Hong, Michael Hicks, Tudor Dumitraş.
NeuraIPS Workshop on Reliable Machine Learning in the Wild, 2016 (NeuraIPS).
Paper Presentation Media Coverage

Journals
Peek-a-Boo: Inferring Program Behaviors in a Virtualized Infrastructure without Introspections.

Sanghyun Hong, Alina Nicolae, Abhinav Srivastava, and Tudor Dumitraș.
Computer & Security, 2018 (COSE).
Paper

Conferences
Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks.

Sanghyun Hong, Pietro Frigo, Yigitcan Kaya, Cristiano Giuffrida, and Tudor Dumitraș.
USENIX Security Symposium, 2019 (USENIX).
Paper Presentation

Shallow-Deep Networks: Understanding and Mitigating Network Overthinking.

Yigitcan Kaya, Sanghyun Hong, and Tudor Dumitraș.
International Conference on Machine Learning, 2019 (ICML).
Paper Presentation Poster Code Website

SENA: Preserving Social Structure for Network Embedding.

*Sanghyun Hong, *Tanmoy Chakraborty, Sungjin Ahn, Ghaith Husari, Noseong Park. (* indicates equal contribution)
ACM Conference on Hypertext and Social Media, 2017 (ACM HT).
Paper

PAGE: Answering Graph Pattern Queries via Knowledge Graph Embedding.

Sanghyun Hong, Noseong Park, Tanmoy Chakraborty, Hyunjoong Kang, Soonhyun Kwon.
International Conference on Big Data, 2018 (BigData).
Paper Presentation

Workshops
Go Serverless: Securing Cloud via Serverless Design Patterns.

Sanghyun Hong, Abhinav Srivastava, William Shambrook, and Tudor Dumitraș.
USENIX Workshop on Hot Topics in Cloud Computing, 2018 (HotCloud 18).
Paper Presentation

On Integrating Knowledge Graph Embedding into SPARQL Query Processing.

Soonhyun Kwon Hyunjoong Kang, Sanghyun Hong, Kookjin Lee, Noseong Park.
International Conference on Web Services, 2018. (ICWS) [Work in Progress Papers]
Paper

Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning.

Rock Stevens, Octavian Suciu, Andrew Ruef, Sanghyun Hong, Michael Hicks, Tudor Dumitraş.
NeuraIPS Workshop on Reliable Machine Learning in the Wild, 2016 (NeuraIPS).
Paper Presentation Media Coverage

Posters
Poster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset

Sanghyun Hong, Tae-hoon Kim, Tudor Dumitraş, Jonghyun Choi
The Network and Distributed System Security Symposium, 2019 (NDSS).
Paper Poster

Manuscripts
Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks

*Sanghyun Hong, *Michael Davinroy, Yiǧitcan Kaya, Stuart Nevans Locke, Ian Rackow, Kevin Kulda, Dana Dachman-Soled, Tudor Dumitraş (* indicates equal contribution)
arXiv Preprint, 2018 (arXiv).
Paper Code

Thesis
A Power Saving Mechanism for Smartphone Modem via Application-based Packet Piggybacking.

Sanghyun Hong
Bachelor Thesis (advised by Prof. Seongsoo Hong).
Thesis