Imbalanced gradients: a subtle cause of overestimated adversarial robustness von Ma, Xingjun, Jiang, Linxi, Huang, Hanxun, Weng, Zejia, Bailey, James, Jiang, Yu-Gang

Volltext

Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks von Xie, Yong, Zheng, Weijie, Huang, Hanxun, Ye, Guangnan, Ma, Xingjun

Volltext bestellen

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models von Li, Yige, Huang, Hanxun, Zhao, Yunhan, Ma, Xingjun, Sun, Jun

Volltext bestellen

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models von Li, Yige, Huang, Hanxun, Zhang, Jiaming, Ma, Xingjun, Jiang, Yu-Gang

Volltext bestellen

Distilling Cognitive Backdoor Patterns within an Image von Huang, Hanxun, Ma, Xingjun, Erfani, Sarah, Bailey, James

Volltext bestellen

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers von Zheng, Weijie, Ma, Xingjun, Huang, Hanxun, Wu, Zuxuan, Jiang, Yu-Gang

Volltext bestellen

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks von Li, Yige, He, Jiabo, Huang, Hanxun, Sun, Jun, Ma, Xingjun, Jiang, Yu-Gang

Volltext bestellen

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness von Ma, Xingjun, Jiang, Linxi, Huang, Hanxun, Weng, Zejia, Bailey, James, Yu-Gang, Jiang

Volltext

LDReg: Local Dimensionality Regularized Self-Supervised Learning von Huang, Hanxun, Campello, Ricardo J. G. B, Erfani, Sarah Monazam, Ma, Xingjun, Houle, Michael E, Bailey, James

Volltext bestellen

Tang lang quan shu sui bi xu ji / Huang Hanxun bian shu.,螳螂拳術隨筆續集 / 黄漢勛編述 von Huang, Hanxun., 黄漢勛

Volltext bestellen

Neural Architecture Search via Combinatorial Multi-Armed Bandit von Huang, Hanxun, Ma, Xingjun, Erfani, Sarah M, Bailey, James

Volltext bestellen

Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks von Xie, Yong, Zheng, Weijie, Huang, Hanxun, Ye, Guangnan, Ma, Xingjun

Volltext

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks on Large Language Models von Li, Yige, Huang, Hanxun, Zhao, Yunhan, Ma, Xingjun, Sun, Jun

Volltext

Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks von Huang, Hanxun, Wang, Yisen, Erfani, Sarah Monazam, Gu, Quanquan, Bailey, James, Ma, Xingjun

Volltext bestellen

Distilling Cognitive Backdoor Patterns within an Image von Huang, Hanxun, Ma, Xingjun, Erfani, Sarah, Bailey, James

Volltext

Unlearnable Examples: Making Personal Data Unexploitable von Huang, Hanxun, Ma, Xingjun, Erfani, Sarah Monazam, Bailey, James, Wang, Yisen

Volltext bestellen

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks von Li, Yige, He, Jiabo, Huang, Hanxun, Sun, Jun, Ma, Xingjun, Yu-Gang, Jiang

Volltext

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models von Li, Yige, Huang, Hanxun, Zhang, Jiaming, Ma, Xingjun, Yu-Gang, Jiang

Volltext

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers von Zheng, Weijie, Ma, Xingjun, Huang, Hanxun, Wu, Zuxuan, Yu-Gang, Jiang

Volltext

Normalized Loss Functions for Deep Learning with Noisy Labels von Ma, Xingjun, Huang, Hanxun, Wang, Yisen, Romano, Simone, Erfani, Sarah, Bailey, James

Volltext bestellen