Sanghyun Hong

78 papers A* 19A 7Journal 44Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs.
CoRR
Zachary Coalson, Bo Fang, Sanghyun Hong
2026 J jnl
Discovering Universal Activation Directions for PII Leakage in Language Models.
CoRR
Leo Marchyok, Zachary Coalson, Sungho Keum, Sooel Son, Sanghyun Hong
2026 J jnl
Fail-Closed Alignment for Large Language Models.
CoRR
Zachary Coalson, Beth Sohler, Aiden Gabriel, Sanghyun Hong
2025 J jnl
Data Therapist: Eliciting Domain Knowledge from Subject Matter Experts Using Large Language Models.
CoRR
Sungbok Shin, Hyeon Jeon, Sanghyun Hong, Niklas Elmqvist
2025 A conf
Demystifying the Resilience of Large Language Model Inference: An End-to-End Perspective.
SC
Yu Sun, Zachary Coalson, Shiyang Chen, Hang Liu, Zhao Zhang, Sanghyun Hong, Bo Fang, Lishan Yang
2025 A conf
Enhancing Audio Deepfake Detection by Improving Representation Similarity of Bonafide Speech.
INTERSPEECH
Seung-Bin Kim, Hyun-seo Shin, Jungwoo Heo, Chan-yeong Lim, Kyo-Won Koo, Jisoo Son, Sanghyun Hong, Souhwan Jung, Ha-Jin Yu
2025 A conf
Evaluating Robustness of Reference-based Phishing Detectors.
AsiaCCS
Eunjin Roh, Sungwoo Jeon, Sooel Son, Sanghyun Hong
2025 J jnl
Hard Work Does Not Always Pay Off: On the Robustness of NAS to Data Poisoning.
Trans. Mach. Learn. Res.
Zachary Coalson, Huazheng Wang, Qingyun Wu, Sanghyun Hong
2025 J jnl
Harnessing Input-Adaptive Inference for Efficient VLN.
CoRR
Dongwoo Kang, Akhil Perincherry, Zachary Coalson, Aiden Gabriel, Stefan Lee, Sanghyun Hong
2025 J jnl
Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions.
CoRR
Tahmid Hasan Prato, Seijoon Kim, Lizhong Chen, Sanghyun Hong
2025 J jnl
IF-GUIDE: Influence Function-Guided Detoxification of LLMs.
CoRR
Zachary Coalson, Juhan Bae, Nicholas Carlini, Sanghyun Hong
2025 J jnl
Inference-Time Noise Addition for Improving Adversarial Robustness of Audio Deepfake Detection System.
IEEE Access
Inho Kim, Thien-Phuc Doan, Sanghyun Hong, Souhwan Jung
2025 J jnl
MADCAT: Combating Malware Detection Under Concept Drift with Test-Time Adaptation.
CoRR
Eunjin Roh, Yigitcan Kaya, Christopher Kruegel, Giovanni Vigna, Sanghyun Hong
2025 J jnl
Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents.
CoRR
Derek Lilienthal, Sanghyun Hong
2025 A* conf
Private Investigator: Extracting Personally Identifiable Information from Large Language Models Using Optimized Prompts.
USENIX Security Symposium
Seongho Keum, Dongwon Shin, Leo Marchyok, Sanghyun Hong, Sooel Son
2025 A* conf
SoK: Watermarking for AI-Generated Content.
SP
Xuandong Zhao, Sam Gunn, Miranda Christ, Jaiden Fairoze, Andrés Fábrega, Nicholas Carlini, Sanjam Garg, Sanghyun Hong, Milad Nasr, Florian Tramèr, Somesh Jha, Lei Li, Yu-Xiang Wang, Dawn Song
2025 J jnl
Understanding and Mitigating Membership Inference Risks of Neural Ordinary Differential Equations.
CoRR
Sanghyun Hong, Fan Wu, Anthony Gruber, Kookjin Lee
2025 J jnl
Visualizationary: Automating Design Feedback for Visualization Designers Using Large Language Models.
IEEE Trans. Vis. Comput. Graph.
Sungbok Shin, Sanghyun Hong, Niklas Elmqvist
2025 A* conf
When Does Wasm Malware Detection Fail? A Systematic Analysis of Their Robustness to Evasion.
ASE
TaeYoung Kim, Sanghak Oh, Kiho Lee, Weihang Wang, Yonghwi Kwon, Sanghyun Hong, Hyoungshick Kim
2024 J jnl
Diffusion Denoising as a Certified Defense against Clean-label Poisoning.
CoRR
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
2024 J jnl
Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search.
CoRR
Zachary Coalson, Huazheng Wang, Qingyun Wu, Sanghyun Hong
2024 A conf
Identifying Contemporaneous and Lagged Dependence Structures by Promoting Sparsity in Continuous-time Neural Networks.
CIKM
Fan Wu, Woojin Cho, David Korotky, Sanghyun Hong, Donsub Rim, Noseong Park, Kookjin Lee
2024 A* conf
LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions.
ICML
Victor Agostinelli, Sanghyun Hong, Lizhong Chen
2024 J jnl
LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions.
CoRR
Victor Agostinelli, Sanghyun Hong, Lizhong Chen
2024 — conf
Message from the DSML Workshop Chairs; DSN-W 2024.
DSN-W
Sanghyun Hong, Bo Fang
2024 A* conf
Operator-Learning-Inspired Modeling of Neural Ordinary Differential Equations.
AAAI
Woojin Cho, Seunghyeon Cho, Hyundong Jin, Jinsung Jeon, Kookjin Lee, Sanghyun Hong, Dongeun Lee, Jonghyun Choi, Noseong Park
2024 A* conf
PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images.
ICLR
Jinsung Jeon, Hyundong Jin, Jonghyun Choi, Sanghyun Hong, Dongeun Lee, Kookjin Lee, Noseong Park
2024 J jnl
PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images.
CoRR
Jinsung Jeon, Hyundong Jin, Jonghyun Choi, Sanghyun Hong, Dongeun Lee, Kookjin Lee, Noseong Park
2024 A* conf
Parameterized Physics-informed Neural Networks for Parameterized PDEs.
ICML
Woojin Cho, Minju Jo, Haksoo Lim, Kookjin Lee, Dongeun Lee, Sanghyun Hong, Noseong Park
2024 J jnl
Parameterized Physics-informed Neural Networks for Parameterized PDEs.
CoRR
Woojin Cho, Minju Jo, Haksoo Lim, Kookjin Lee, Dongeun Lee, Sanghyun Hong, Noseong Park
2024 J jnl
PrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips.
CoRR
Zachary Coalson, Jeonghyun Woo, Shiyang Chen, Yu Sun, Lishan Yang, Prashant J. Nair, Bo Fang, Sanghyun Hong
2024 A* conf
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models.
NeurIPS
Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini
2024 J jnl
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models.
CoRR
Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini
2024 J jnl
SoK: Watermarking for AI-Generated Content.
CoRR
Xuandong Zhao, Sam Gunn, Miranda Christ, Jaiden Fairoze, Andrés Fábrega, Nicholas Carlini, Sanjam Garg, Sanghyun Hong, Milad Nasr, Florian Tramèr, Somesh Jha, Lei Li, Yu-Xiang Wang, Dawn Song
2024 J jnl
Visualizationary: Automating Design Feedback for Visualization Designers using LLMs.
CoRR
Sungbok Shin, Sanghyun Hong, Niklas Elmqvist
2024 — conf
When Do "More Contexts" Help with Sarcasm Recognition?
LREC/COLING
Ojas Nimase, Sanghyun Hong
2024 J jnl
When Do "More Contexts" Help with Sarcasm Recognition?
CoRR
Ojas Nimase, Sanghyun Hong
2024 J jnl
You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models.
CoRR
Eric Slyman, Anirudh Kanneganti, Sanghyun Hong, Stefan Lee
2024 A conf
You Only Perturb Once: Bypassing (Robust) Ad-Blockers Using Universal Adversarial Perturbations.
ACSAC
Dongwon Shin, Suyoung Lee, Sanghyun Hong, Sooel Son
2023 J jnl
A Scanner Deeply: Predicting Gaze Heatmaps on Visualizations Using Crowdsourced Eye Movement Data.
IEEE Trans. Vis. Comput. Graph.
Sungbok Shin, Sunghyo Chung, Sanghyun Hong, Niklas Elmqvist
2023 A* conf
BERT Lost Patience Won't Be Robust to Adversarial Slowdown.
NeurIPS
Zachary Coalson, Gabriel Ritter, Rakesh Bobba, Sanghyun Hong
2023 J jnl
BERT Lost Patience Won't Be Robust to Adversarial Slowdown.
CoRR
Zachary Coalson, Gabriel Ritter, Rakesh Bobba, Sanghyun Hong
2023 A* conf
Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator.
ICML
Sicheng Zhu, Bang An, Furong Huang, Sanghyun Hong
2023 J jnl
Operator-learning-inspired Modeling of Neural Ordinary Differential Equations.
CoRR
Woojin Cho, Seunghyeon Cho, Hyundong Jin, Jinsung Jeon, Kookjin Lee, Sanghyun Hong, Dongeun Lee, Jonghyun Choi, Noseong Park
2023 J jnl
Perceptual Pat: A Virtual Human System for Iterative Visualization Design.
CoRR
Sungbok Shin, Sanghyun Hong, Niklas Elmqvist
2023 A* conf
Perceptual Pat: A Virtual Human Visual System for Iterative Visualization Design.
CHI
Sungbok Shin, Sanghyun Hong, Niklas Elmqvist
2023 — conf
Publishing Efficient On-device Models Increases Adversarial Vulnerability.
SaTML
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
2022 J jnl
AdamNODEs: When Neural ODE Meets Adaptive Moment Estimation.
CoRR
Suneghyeon Cho, Sanghyun Hong, Kookjin Lee, Noseong Park
2022 A* conf
Data Poisoning Won't Save You From Facial Recognition.
ICLR
Evani Radiya-Dixit, Sanghyun Hong, Nicholas Carlini, Florian Tramèr
2022 A* conf
Handcrafted Backdoors in Deep Neural Networks.
NeurIPS
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
2022 A conf
Improving cross-platform binary analysis using representation learning via graph alignment.
ISSTA
Geunwoo Kim, Sanghyun Hong, Michael Franz, Dokyung Song
2022 J jnl
Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting.
CoRR
Fan Wu, Sanghyun Hong, Donsub Rim, Noseong Park, Kookjin Lee
2022 J jnl
Publishing Efficient On-device Models Increases Adversarial Vulnerability.
CoRR
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
2022 J jnl
Time Series Forecasting with Hypernetworks Generating Parameters in Advance.
CoRR
Jaehoon Lee, Chan Kim, Gyumin Lee, Haksoo Lim, Jeongwhan Choi, Kookjin Lee, Dongeun Lee, Sanghyun Hong, Noseong Park
2022 A* conf
Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets.
CCS
Florian Tramèr, Reza Shokri, Ayrton San Joaquin, Hoang Le, Matthew Jagielski, Sanghyun Hong, Nicholas Carlini
2022 J jnl
Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets.
CoRR
Florian Tramèr, Reza Shokri, Ayrton San Joaquin, Hoang Le, Matthew Jagielski, Sanghyun Hong, Nicholas Carlini
2021 A* conf
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference.
ICLR
Sanghyun Hong, Yigitcan Kaya, Ionut-Vlad Modoranu, Tudor Dumitras
2021 — —
Building Secure and Reliable Deep Learning Systems from a Systems Security Perspective.
Sanghyun Hong
2021 — conf
Certified Malware in South Korea: A Localized Study of Breaches of Trust in Code-Signing PKI Ecosystem.
ICICS (1)
Bum Jun Kwon, Sanghyun Hong, Yuseok Jeon, Doowon Kim
2021 J jnl
Handcrafted Backdoors in Deep Neural Networks.
CoRR
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
2021 A* conf
Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes.
NeurIPS
Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Tudor Dumitras
2021 J jnl
Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes.
CoRR
Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yigitcan Kaya, Tudor Dumitras
2020 J jnl
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference.
CoRR
Sanghyun Hong, Yigitcan Kaya, Ionut-Vlad Modoranu, Tudor Dumitras
2020 J jnl
How to 0wn NAS in Your Spare Time.
CoRR
Sanghyun Hong, Michael Davinroy, Yigitcan Kaya, Dana Dachman-Soled, Tudor Dumitras
2020 A* conf
How to 0wn the NAS in Your Spare Time.
ICLR
Sanghyun Hong, Michael Davinroy, Yigitcan Kaya, Dana Dachman-Soled, Tudor Dumitras
2020 J jnl
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping.
CoRR
Sanghyun Hong, Varun Chandrasekaran, Yigitcan Kaya, Tudor Dumitras, Nicolas Papernot
2020 J jnl
On the Effectiveness of Regularization Against Membership Inference Attacks.
CoRR
Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras
2019 J jnl
Poster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset.
CoRR
Sanghyun Hong, Tae-Hoon Kim, Tudor Dumitras, Jonghyun Choi
2019 A* conf
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking.
ICML
Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras
2019 A* conf
Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks.
USENIX Security Symposium
Sanghyun Hong, Pietro Frigo, Yigitcan Kaya, Cristiano Giuffrida, Tudor Dumitras
2019 J jnl
Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks.
CoRR
Sanghyun Hong, Pietro Frigo, Yigitcan Kaya, Cristiano Giuffrida, Tudor Dumitras
2018 — conf
Go Serverless: Securing Cloud via Serverless Design Patterns.
HotCloud
Sanghyun Hong, Abhinav Srivastava, William Shambrook, Tudor Dumitras
2018 A conf
On Integrating Knowledge Graph Embedding into SPARQL Query Processing.
ICWS
Hyunjoong Kang, Sanghyun Hong, Kookjin Lee, Noseong Park, Soonhyun Kwon
2018 — conf
PAGE: Answering Graph Pattern Queries via Knowledge Graph Embedding.
BigData Congress
Sanghyun Hong, Noseong Park, Tanmoy Chakraborty, Hyunjoong Kang, Soonhyun Kwon
2018 J jnl
Peek-a-boo: Inferring program behaviors in a virtualized infrastructure without introspection.
Comput. Secur.
Sanghyun Hong, Alina Nicolae, Abhinav Srivastava, Tudor Dumitras
2018 J jnl
Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks.
CoRR
Sanghyun Hong, Michael Davinroy, Yigitcan Kaya, Stuart Nevans Locke, Ian Rackow, Kevin Kulda, Dana Dachman-Soled, Tudor Dumitras
2017 — conf
SENA: Preserving Social Structure for Network Embedding.
HT
Sanghyun Hong, Tanmoy Chakraborty, Sungjin Ahn, Ghaith Husari, Noseong Park
2017 J jnl
Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning.
CoRR
Rock Stevens, Octavian Suciu, Andrew Ruef, Sanghyun Hong, Michael W. Hicks, Tudor Dumitras