Volgen
Hanxun Huang
Titel
Geciteerd door
Geciteerd door
Jaar
Normalized Loss Functions for Deep Learning with Noisy Labels
X Ma, H Huang, Y Wang, S Romano, S Erfani, J Bailey
International Conference on Machine Learning (ICML), 2020
4582020
Unlearnable Examples: Making Personal Data Unexploitable
H Huang, X Ma, SM Erfani, J Bailey, Y Wang
International Conference on Learning Representations (ICLR), 2021
1642021
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks
H Huang, Y Wang, SM Erfani, Q Gu, J Bailey, X Ma
Advances in Neural Information Processing Systems (NeurIPS), 2021
1082021
Distilling Cognitive Backdoor Patterns within an Image
H Huang, X Ma, S Erfani, J Bailey
International Conference on Learning Representations (ICLR), 2023
142023
Neural Architecture Search via Combinatorial Multi-Armed Bandit
H Huang, X Ma, SM Erfani, J Bailey
International Joint Conference on Neural Networks (IJCNN), 2021
62021
Multi-Trigger Backdoor Attacks: More Triggers, More Threats
Y Li, X Ma, J He, H Huang, YG Jiang
arXiv preprint arXiv:2401.15295, 2024
52024
Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness
X Ma, L Jiang, H Huang, Z Weng, J Bailey, YG Jiang
Machine Learning, 2023
52023
LDReg: Local Dimensionality Regularized Self-Supervised Learning
H Huang, RJGB Campello, SM Erfani, X Ma, ME Houle, J Bailey
International Conference on Learning Representations (ICLR), 2024
32024
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models
Y Li, H Huang, Y Zhao, X Ma, J Sun
arXiv preprint arXiv:2408.12798, 2024
2024
Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
W Zheng, X Ma, H Huang, Z Wu, YG Jiang
arXiv preprint arXiv:2408.01705, 2024
2024
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–10