홍상현 오레곤 주립 대학교

Oregon State University
Computer Science Dept.
Cybersecurity | AI
Contact Information

Office: Room 4103, Kelley Engineering Center (KEC)
2500 NW Monroe Ave
Corvallis, OR 97331 USA
Office Hours: Tu/Th: 2 - 3 pm

          

Press

06.2023

OSU AI News

04.2022

TechXplore
Techradar.pro

06.2021

TechTalks

05.2021

Dev Podcast
MIT Tech Review

02.2021

USENIX Enigma 2021
(Ted Talk for Security)

Teaching

Fall 23 CS499/579: TML
Spring 23 CS370: Intro to Sec.
CS499/579: TML
Winter 23 CS344: OS I
Spring 22 CS344: OS I
Winter 21 CS499/599: MLSec.
Students [Full list]

David Korotky (PhD, CS)
Tahmid Prato (PhD, CS)
Jose Escamilla (PhD, CS
  co-advise w. Huazheng Wang)
Gabriel Ritter (PhD, CS,
  co-advise w. Rakesh Bobba)
Anirudh Kanneganti (MS, CS)
Zach Coalson (BS, CS)
Evan Mrazik (BS, CS)
Leo Marchyok (BS, CS)
Colin Pannikkat (BS, CS)
Nyx (CS)

Alumni

'24: Ramya Jayaraman (MS, AI)
'23: Hoang Le (MS, CS)
'22: Peter M-Stevens (BS, CS)
'22: Ryan Little (BS, CS)
  Now a PhD student at UMD

Referred Papers


Color Palettes: Conferences | Journals | Workshops | Preprints
2024

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, and Nicholas Carlini
arXiv Preprint. 2024.
PDF

Diffusion Denoising as a Certified Defense against Clean-label Poisoning Attacks
Sanghyun Hong, Nicholas Carlini, and Alexey Kurakin
arXiv Preprint. 2024.
PDF

When Do "More Contexts" Help with Sarcasm Recognition?
Ojas Nimase and Sanghyun Hong
The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING). 2024
PDF | Code

Extension of Physics-informed Neural Networks to Solving Parameterized PDEs
Woojin Cho, Minju Jo, Haksoo Lim, Kookjin Lee, Dongeun Lee, Sanghyun Hong, and Noseong Park
International Conference on Learning Representations (ICLR) Workshop
on AI4DifferentialEquations in Science (AI4DiffEqtnsInSci). 2024
PDF

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
Jinsung Jeon, Hyundong Jin, Jonghyun Choi, Sanghyun Hong, Dongeun Lee, Kookjin Lee, and Noseong Park
International Conference on Learning Representations (ICLR). 2024
PDF | Code

Operator-learning-inspired Modeling of Neural Ordinary Differential Equations
Woojin Cho, Seunghyeon Cho, Hyundong Jin, Jinsung Jeon, Kookjin Lee, Sanghyun Hong, Dongeun Lee, Jonghyun Choi, Noseong Park
The 38th Annual AAAI Conference on Artificial Intelligence (AAAI). 2024.
PDF | Talk & Poster

2023

HyperNetwork Approximating Future Parameters for Time Series Forecasting under Temporal Drifts
Jaehoon Lee, Chan Kim, Gyumin Lee, Haksoo Lim, Jeongwhan Choi, Kookjin Lee, Dongeun Lee, Sanghyun Hong, Noseong Park
Advances in Neural Information Processing Systems Workshop
on Distribution Shifts (NeurIPS DistShift). 2023.
PDF | Code | Talk & Poster (on NeurIPS'23 Website)

BERT Lost Patience Won't Be Robust to Adversarial Slowdown
Zachery Coalson, Gabriel Ritter, Rakesh Bobba, Sanghyun Hong
Advances in Neural Information Processing Systems (NeurIPS). 2023.
PDF | Code | Talk & Poster (on NeurIPS'23 Website)

A Stability Analysis of Neural Networks and Its Application to Tsunami Early Warning
Donsub Rim, Sanah Suri, Sanghyun Hong, Kookjin Lee, Randall J LeVequestrong
Earth arXiv. 2023.
PDF

Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator
Sicheng Zhu, Bang An, Furong Huang, and Sanghyun Hong
International Conference on Machine Learning (ICML). 2023.
PDF | Code | Talk & Poster (on ICML'23 Website)

Perceptual Pat: A Virtual Human Visual System for Iterative Visualization Design
Sungbok Shin, Sanghyun Hong, and Niklas Elmqvist
ACM Conference on Human Factors in Computing Systems (CHI). 2023.
PDF | Teaser

Publishing Efficient On-device Models Increases Adversarial Vulnerability
Sanghyun Hong, Nicholas Carlini, and Alexey Kurakin
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). 2023.
PDF | Talk

2022

Will SOC Telemetry Data Improve Predictive Models of User Riskiness? A Work in Progress
Michael Curry, Byron Marshall, Forough Shadbad, and Sanghyun Hong
AIS SIGSEC 17th Workshop on Information Security and Privacy (WISP). 2022.
PDF

Handcrafted Backdoors in Deep Neural Networks
Sanghyun Hong, Nicholas Carlini, and Alexey Kurakin
Advances in Neural Information Processing Systems (NeurIPS). 2022. [Oral]
PDF | Code & Supp. | Talk (on NeurIPS'22 Website)

A Scanner Deeply: Predicting Gaze Heatmaps on Visualizations Using Crowdsourced Eye Movement Data
Sungbok Shin, Sunghyo Chung, Sanghyun Hong, Niklas Elmqvist
IEEE Transactions on Visualization and Computer Graphics (Proc. IEEE VIS 2022). 2022. (IF: 5.226)
PDF | Code & Data

Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets
Florian Tramèr, Reza Shokri, Ayrton San Joaquin, Hoang Le, Matthew Jagielski, Sanghyun Hong,
Nicholas Carlini
(*authors ordered reverse-alphabetically)
The ACM Conference on Computer and Communications Security (CCS). 2022.
PDF | Code | Media

AdamNODEs: When Neural ODE Meets Adaptive Moment Estimation
Seunghyeon Cho, Sanghyun Hong, Kookjin Lee, Noseong Park
International Conference on Machine Learning (ICML) Workshop
on Continuous-Time Methods for Machine Learning. 2022.
PDF | Code

Improving Cross-Platform Binary Analysis Using Representation Learning via Graph Alignment
Geunwoo Kim, Sanghyun Hong, Michael Franz, Dokyung Song
The ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA). 2022.
PDF | Code

Data Poisoning Won't Save You From Facial Recognition
Evani Radiya-Dixit, Sanghyun Hong, Nicholas Carlini, Florian Tramer
International Conference on Learning Representations (ICLR). 2022.
PDF | Code | Poster

2021

Qu-ANTI-zation: Exploiting Neural Network Quantization for Achieving Adversarial Outcomes
Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, and Tudor Dumitraș
Advances in Neural Information Processing Systems (NeurIPS). 2021.
PDF | Code | Poster

A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
*Sanghyun Hong, *Yigitcan Kaya, Ionuţ-Vlad Modoranu, and Tudor Dumitraș(* equal contribution)
International Conference on Learning Representations (ICLR). 2021. [Spotlight]
PDF | Code | Spotlight Presentation

Certified Malware in South Korea: A Localized Study of Breaches of Trust
in Code-Signing PKI Ecosystem

Bumjun Kwon, Sanghyun Hong, Yuseok Jeon, Doowon Kim
International Conference on Information and Communications Security (ICICS). 2021.
PDF

A Sound Mind in a Vulnerable Body:
Practical Hardware Attacks on Deep Learning

Sanghyun Hong
USENIX Enigma (Enigma). 2021.
Presentation

2020

On the Effectiveness of Regularization Against Membership Inference Attacks
Yiǧitcan Kaya, Sanghyun Hong, and Tudor Dumitraş
arXiv Preprint. 2020.
PDF

On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
Sanghyun Hong, Varun Chandrasekaran, Yiǧitcan Kaya, Tudor Dumitraş, and Nicolas Papernot
arXiv Preprint. 2020.
PDF | Code

How to 0wn NAS in Your Spare Time
Sanghyun Hong, Michael Davinroy, Yigitcan Kaya, Dana Dachman-Soled, and Tudor Dumitraș
International Conference on Learning Representations (ICLR). 2020.
PDF | Code | Poster

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
Proceedings of The 28th USENIX Security Symposium (USENIX Security). 2019.
PDF | Presentation

Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
Yigitcan Kaya, Sanghyun Hong, and Tudor Dumitraș
International Conference on Machine Learning (ICML). 2019.
PDF | Code

Poster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset
Sanghyun Hong, Tae-hoon Kim, Tudor Dumitraş, and Jonghyun Choi
The Network and Distributed System Security Symposium (NDSS). 2019.
PDF | Code | Poster

Peek-a-Boo: Inferring Program Behaviors in a Virtualized Infrastructure without Introspection
Sanghyun Hong, Alina Nicolae, Abhinav Srivastava, and Tudor Dumitraş
Computer & Security (COSE). 2019.
PDF

2018

Go Serverless: Securing Cloud via Serverless Design Patterns
Sanghyun Hong, Abhinav Srivastava, William Shambrook, and Tudor Dumitraș
10th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud). 2018.
PDF | Slides

PAGE: Answering Graph Pattern Queries via Knowledge Graph Embedding
Sanghyun Hong, Noseong Park, Tanmoy Chakraborty, Hyunjoong Kang, and Soonhyun Kwon
International Conference on Big Data (Big Data). 2018
Paper | Slides

On Integrating Knowledge Graph Embedding into SPARQL Query Processing
Soonhyun Kwon, Hyunjoong Kang, Sanghyun Hong, Kookjin Lee, and Noseong Park
IEEE International Conference on Web Services (ICWS). 2018
Paper

2017

SENA: Preserving Social Structure for Network Embedding
*Sanghyun Hong, *Tanmoy Chakraborty, Sungjin Ahn, Ghaith Husari, and Noseong Park
(* equal contribution)
ACM Conference on Hypertext and Social Media (ACM HT). 2017.
Paper

Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning
Rock Stevens, Octavian Suciu, Andrew Ruef, Sanghyun Hong, Michael Hicks, and Tudor Dumitraş
NeurIPS Workshop on Reliable Machine Learning in the Wild (NeurIPS). 2017.
Paper | Slides | Media