activity
20142023
most citedCValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility

13 citations · 15 across the 13 of their papers we have counts for

collaborators

13 papers

cs.CV2023

Model Inversion Attack via Dynamic Memory Learning

Gege Qi, YueFeng Chen, Xiaofeng Mao +4

Model Inversion (MI) attacks aim to recover the private training data from the target model, which has raised security concerns about the deployment of DNNs in practice. Recent adv…

cs.CV2023

Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging

Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao +5

Fast Adversarial Training (FAT) not only improves the model robustness but also reduces the training cost of standard adversarial training. However, fast adversarial training often…

cs.SD2023

Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training

Gege Qi, Yuefeng Chen, Xiaofeng Mao +4

Developing a practically-robust automatic speech recognition (ASR) is challenging since the model should not only maintain the original performance on clean samples, but also achie…

cs.CL202313 cited

CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility

Guohai Xu, Jiayi Liu, Ming Yan +11

With the rapid evolution of large language models (LLMs), there is a growing concern that they may pose risks or have negative social impacts. Therefore, evaluation of human values…

cs.CV2023

ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing

Xiaodan Li, Yuefeng Chen, Yao Zhu +3

Recent studies have shown that higher accuracy on ImageNet usually leads to better robustness against different corruptions. Therefore, in this paper, instead of following the trad…

cs.SD2023

TransAudio: Towards the Transferable Adversarial Audio Attack via Learning Contextualized Perturbations

Qi Gege, Yuefeng Chen, Xiaofeng Mao +5

In a transfer-based attack against Automatic Speech Recognition (ASR) systems, attacks are unable to access the architecture and parameters of the target model. Existing attack met…