Alert button
Picture for Heng Pan

Heng Pan

Alert button

vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer

May 26, 2023
Xinchi Qiu, Heng Pan, Wanru Zhao, Chenyang Ma, Pedro P. B. Gusmao, Nicholas D. Lane

Figure 1 for vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer
Figure 2 for vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer
Figure 3 for vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer
Figure 4 for vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer

Most work in privacy-preserving federated learning (FL) has been focusing on horizontally partitioned datasets where clients share the same sets of features and can train complete models independently. However, in many interesting problems, individual data points are scattered across different clients/organizations in a vertical setting. Solutions for this type of FL require the exchange of intermediate outputs and gradients between participants, posing a potential risk of privacy leakage when privacy and security concerns are not considered. In this work, we present vFedSec - a novel design with an innovative Secure Layer for training vertical FL securely and efficiently using state-of-the-art security modules in secure aggregation. We theoretically demonstrate that our method does not impact the training performance while protecting private data effectively. Empirically results also show its applicability with extensive experiments that our design can achieve the protection with negligible computation and communication overhead. Also, our method can obtain 9.1e2 ~ 3.8e4 speedup compared to widely-adopted homomorphic encryption (HE) method.

* Generalised extension from our previous work: arXiv:2305.11236 
Viaarxiv icon

Efficient Vertical Federated Learning with Secure Aggregation

May 18, 2023
Xinchi Qiu, Heng Pan, Wanru Zhao, Chenyang Ma, Pedro Porto Buarque de Gusmão, Nicholas D. Lane

Figure 1 for Efficient Vertical Federated Learning with Secure Aggregation
Figure 2 for Efficient Vertical Federated Learning with Secure Aggregation
Figure 3 for Efficient Vertical Federated Learning with Secure Aggregation
Figure 4 for Efficient Vertical Federated Learning with Secure Aggregation

The majority of work in privacy-preserving federated learning (FL) has been focusing on horizontally partitioned datasets where clients share the same sets of features and can train complete models independently. However, in many interesting problems, such as financial fraud detection and disease detection, individual data points are scattered across different clients/organizations in vertical federated learning. Solutions for this type of FL require the exchange of gradients between participants and rarely consider privacy and security concerns, posing a potential risk of privacy leakage. In this work, we present a novel design for training vertical FL securely and efficiently using state-of-the-art security modules for secure aggregation. We demonstrate empirically that our method does not impact training performance whilst obtaining 9.1e2 ~3.8e4 speedup compared to homomorphic encryption (HE).

* Federated Learning Systems (FLSys) Workshop @ MLSys 2023 
Viaarxiv icon

Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders

Apr 25, 2023
Heng Pan, Chenyang Liu, Wenxiao Wang, Li Yuan, Hongfa Wang, Zhifeng Li, Wei Liu

Figure 1 for Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders
Figure 2 for Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders
Figure 3 for Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders
Figure 4 for Img2Vec: A Teacher of High Token-Diversity Helps Masked AutoEncoders

We present a pipeline of Image to Vector (Img2Vec) for masked image modeling (MIM) with deep features. To study which type of deep features is appropriate for MIM as a learning target, we propose a simple MIM framework with serials of well-trained self-supervised models to convert an Image to a feature Vector as the learning target of MIM, where the feature extractor is also known as a teacher model. Surprisingly, we empirically find that an MIM model benefits more from image features generated by some lighter models (e.g., ResNet-50, 26M) than from those by a cumbersome teacher like Transformer-based models (e.g., ViT-Large, 307M). To analyze this remarkable phenomenon, we devise a novel attribute, token diversity, to evaluate the characteristics of generated features from different models. Token diversity measures the feature dissimilarity among different tokens. Through extensive experiments and visualizations, we hypothesize that beyond the acknowledgment that a large model can improve MIM, a high token-diversity of a teacher model is also crucial. Based on the above discussion, Img2Vec adopts a teacher model with high token-diversity to generate image features. Img2Vec pre-trained on ImageNet unlabeled data with ViT-B yields 85.1\% top-1 accuracy on fine-tuning. Moreover, we scale up Img2Vec on larger models, ViT-L and ViT-H, and get $86.7\%$ and $87.5\%$ accuracy respectively. It also achieves state-of-the-art results on other downstream tasks, e.g., 51.8\% mAP on COCO and 50.7\% mIoU on ADE20K. Img2Vec is a simple yet effective framework tailored to deep feature MIM learning, accomplishing superb comprehensive performance on representative vision tasks.

Viaarxiv icon

Attacking Adversarial Attacks as A Defense

Jun 09, 2021
Boxi Wu, Heng Pan, Li Shen, Jindong Gu, Shuai Zhao, Zhifeng Li, Deng Cai, Xiaofei He, Wei Liu

Figure 1 for Attacking Adversarial Attacks as A Defense
Figure 2 for Attacking Adversarial Attacks as A Defense
Figure 3 for Attacking Adversarial Attacks as A Defense
Figure 4 for Attacking Adversarial Attacks as A Defense

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we find that the adversarial attacks can also be vulnerable to small perturbations. Namely, on adversarially-trained models, perturbing adversarial examples with a small random noise may invalidate their misled predictions. After carefully examining state-of-the-art attacks of various kinds, we find that all these attacks have this deficiency to different extents. Enlightened by this finding, we propose to counter attacks by crafting more effective defensive perturbations. Our defensive perturbations leverage the advantage that adversarial training endows the ground-truth class with smaller local Lipschitzness. By simultaneously attacking all the classes, the misled predictions with larger Lipschitzness can be flipped into correct ones. We verify our defensive perturbation with both empirical experiments and theoretical analyses on a linear model. On CIFAR10, it boosts the state-of-the-art model from 66.16% to 72.66% against the four attacks of AutoAttack, including 71.76% to 83.30% against the Square attack. On ImageNet, the top-1 robust accuracy of FastAT is improved from 33.18% to 38.54% under the 100-step PGD attack.

Viaarxiv icon

Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network

Sep 28, 2020
Heng Pan

Figure 1 for Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network
Figure 2 for Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network
Figure 3 for Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network
Figure 4 for Cloud Removal for Remote Sensing Imagery via Spatial Attention Generative Adversarial Network

Optical remote sensing imagery has been widely used in many fields due to its high resolution and stable geometric properties. However, remote sensing imagery is inevitably affected by climate, especially clouds. Removing the cloud in the high-resolution remote sensing satellite image is an indispensable pre-processing step before analyzing it. For the sake of large-scale training data, neural networks have been successful in many image processing tasks, but the use of neural networks to remove cloud in remote sensing imagery is still relatively small. We adopt generative adversarial network to solve this task and introduce the spatial attention mechanism into the remote sensing imagery cloud removal task, proposes a model named spatial attention generative adversarial network (SpA GAN), which imitates the human visual mechanism, and recognizes and focuses the cloud area with local-to-global spatial attention, thereby enhancing the information recovery of these areas and generating cloudless images with better quality...

Viaarxiv icon