103 citations · 303 across the 14 of their papers we have counts for
15 papers
Publishing Efficient On-device Models Increases Adversarial Vulnerability
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
Recent increases in the computational demands of deep neural networks (DNNs) have sparked interest in efficient deep learning mechanisms, e.g., quantization or pruning. These mecha…
Time Series Forecasting with Hypernetworks Generating Parameters in Advance
Jaehoon Lee, Chan Kim, Gyumin Lee +6
Forecasting future outcomes from recent time series data is not easy, especially when the future data are different from the past (i.e. time series are under temporal drifts). Exis…
Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting
Fan Wu, Sanghyun Hong, Donsub Rim +2
Continuous-time dynamics models, such as neural ordinary differential equations, have enabled the modeling of underlying dynamics in time-series data and accurate forecasting. Howe…
AdamNODEs: When Neural ODE Meets Adaptive Moment Estimation
Suneghyeon Cho, Sanghyun Hong, Kookjin Lee +1
Recent work by Xia et al. leveraged the continuous-limit of the classical momentum accelerated gradient descent and proposed heavy-ball neural ODEs. While this model offers computa…
Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets
Florian Tramèr, Reza Shokri, Ayrton San Joaquin +4
We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak signifi…
Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes
Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yiğitcan Kaya +1
Quantization is a popular technique that the parameter representation of a neural network from floating-point numbers into lower-precision ones (, 8-bit integers…
Handcrafted Backdoors in Deep Neural Networks
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
When machine learning training is outsourced to third parties, become practical as the third party who trains the model may act maliciously to inject hidden be…
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
Sanghyun Hong, Yiğitcan Kaya, Ionuţ-Vlad Modoranu +1
Recent increases in the computational demands of deep neural networks (DNNs), combined with the observation that most input samples require only simple models, have sparked interes…
On the Effectiveness of Regularization Against Membership Inference Attacks
Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras
Deep learning models often raise privacy concerns as they leak information about their training data. This enables an adversary to determine whether a data point was in a model's t…
On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping
Sanghyun Hong, Varun Chandrasekaran, Yiğitcan Kaya +2
Machine learning algorithms are vulnerable to data poisoning attacks. Prior taxonomies that focus on specific scenarios, e.g., indiscriminate or targeted, have enabled defenses for…
How to 0wn NAS in Your Spare Time
Sanghyun Hong, Michael Davinroy, Yiğitcan Kaya +2
New data processing pipelines and novel network architectures increasingly drive the success of deep learning. In consequence, the industry considers top-performing architectures a…
Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks
Sanghyun Hong, Pietro Frigo, Yiğitcan Kaya +2
Deep neural networks (DNNs) have been shown to tolerate "brain damage": cumulative changes to the network's parameters (e.g., pruning, numerical perturbations) typically result in…
Poster: On the Feasibility of Training Neural Networks with Visibly Watermarked Dataset
Sanghyun Hong, Tae-hoon Kim, Tudor Dumitraş +1
As there are increasing needs of sharing data for machine learning, there is growing attention for the owners of the data to claim the ownership. Visible watermarking has been an e…
Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks
Sanghyun Hong, Michael Davinroy, Yiǧitcan Kaya +5
Recent work has introduced attacks that extract the architecture information of deep neural networks (DNN), as this knowledge enhances an adversary's capability to conduct black-bo…
Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning
Rock Stevens, Octavian Suciu, Andrew Ruef +3
Governments and businesses increasingly rely on data analytics and machine learning (ML) for improving their competitive edge in areas such as consumer satisfaction, threat intelli…