27 citations · 40 across the 16 of their papers we have counts for
16 papers
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
Hao Li, Lijun Li, Zhenghao Lu +4
With rapid advancement and increasing accessibility of LLMs, fine-tuning aligned models has become a critical step for adapting them to real-world applications, which makes the saf…
Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks
Yangqi Feng, Shing-Ho J. Lin, Baoyuan Gao +1
Recent research has revealed that high compression of Deep Neural Networks (DNNs), e.g., massive pruning of the weight matrix of a DNN, leads to a severe drop in accuracy and susce…
When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices
Pengyu Zhang, Yingjie Liu, Yingbo Zhou +4
Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy mem…
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
Jun Xia, Zhihao Yue, Yingbo Zhou +3
Due to the popularity of Artificial Intelligence (AI) technology, numerous backdoor attacks are designed by adversaries to mislead deep neural network predictions by manipulating t…
Continual Learning via Manifold Expansion Replay
Zihao Xu, Xuan Tang, Yufei Shi +4
In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual le…
EqGAN: Feature Equalization Fusion for Few-shot Image Generation
Yingbo Zhou, Zhihao Yue, Yutong Ye +3
Due to the absence of fine structure and texture information, existing fusion-based few-shot image generation methods suffer from unsatisfactory generation quality and diversity. T…
Is Aggregation the Only Choice? Federated Learning via Layer-wise Model Recombination
Ming Hu, Zhihao Yue, Xiaofei Xie +6
Although Federated Learning (FL) enables global model training across clients without compromising their raw data, due to the unevenly distributed data among clients, existing Fede…
Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representations
Jianzhang Zheng, Hao Shen, Jian Yang +5
Autoencoders have achieved great success in various computer vision applications. The autoencoder learns appropriate low dimensional image representations through the self-supervis…
A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold
Yanhong Fei, Xian Wei, Yingjie Liu +2
Although Deep Learning (DL) has achieved success in complex Artificial Intelligence (AI) tasks, it suffers from various notorious problems (e.g., feature redundancy, and vanishing…
CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning
Pengyu Zhang, Yingbo Zhou, Ming Hu +2
Federated learning (FL) has been proposed to enable distributed learning on Artificial Intelligence Internet of Things (AIoT) devices with guarantees of high-level data privacy. Si…
HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation
Jun Xia, Yi Zhang, Zhihao Yue +3
Federated learning (FL) has been recognized as a privacy-preserving distributed machine learning paradigm that enables knowledge sharing among various heterogeneous artificial inte…
FedMR: Fedreated Learning via Model Recombination
Ming Hu, Zhihao Yue, Zhiwei Ling +2
As a promising privacy-preserving machine learning method, Federated Learning (FL) enables global model training across clients without compromising their confidential local data.…
Model-Contrastive Learning for Backdoor Defense
Zhihao Yue, Jun Xia, Zhiwei Ling +4
Due to the popularity of Artificial Intelligence (AI) techniques, we are witnessing an increasing number of backdoor injection attacks that are designed to maliciously threaten Dee…
Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation
Jun Xia, Ting Wang, Jiepin Ding +2
Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs).Although the state-of-th…
O-ViT: Orthogonal Vision Transformer
Yanhong Fei, Yingjie Liu, Xian Wei +1
Inspired by the tremendous success of the self-attention mechanism in natural language processing, the Vision Transformer (ViT) creatively applies it to image patch sequences and a…
Boost Neural Networks by Checkpoints
Feng Wang, Guoyizhe Wei, Qiao Liu +3
Training multiple deep neural networks (DNNs) and averaging their outputs is a simple way to improve the predictive performance. Nevertheless, the multiplied training cost prevents…