Sanghyun Hong

secure-ai.systems [email protected]

Oregon State University United States I am an AI-hacker who works on finding the security/privacy risks of AI-enabled systems and making them secure!

Results 2 repositories owned by


Sanghyun Hong

DeepSloth

15

Stars

1

Forks

Watchers

[ICLR 2021: Spotlight] Source code for the paper "A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference"

adversarial-examples

multi-exit-architectures

DeepRecon

16

Stars

6

Forks

Watchers

[arXiv'18] Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks

neural-network-architectures

security-vulnerability

side-channel-attacks