2.3k citations · 7.1k across the 22 of their papers we have counts for
Showing cs.CRShow all
3 papers · 1 filter
cs.CR2024
Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
Sanghyun Hong, Nicholas Carlini, Alexey Kurakin
We present a certified defense to clean-label poisoning attacks under -norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bou…
cs.CR2022
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…
cs.CR2021★ 20 cited
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…