Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient
Accumulation
- URL: http://arxiv.org/abs/2401.01575v1
- Date: Wed, 3 Jan 2024 07:00:32 GMT
- Title: Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient
Accumulation
- Authors: Xuannan Liu and Yaoyao Zhong and Weihong Deng and Hongzhi Shi and
Xingchen Cui and Yunfeng Yin and Dongchao Wen
- Abstract summary: A new type of adversarial privacy cloak (class-universal) can be applied to all the images of regular users.
We propose Gradient Accumulation (GA) to aggregate multiple small-batch gradients into a one-step iterative gradient to enhance the gradient stability and reduce the usage of quantization operations.
Experiments show that our proposed method achieves high performance on the Privacy-Commons dataset against black-box face recognition models.
- Score: 46.81652932809355
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The blooming of social media and face recognition (FR) systems has increased
people's concern about privacy and security. A new type of adversarial privacy
cloak (class-universal) can be applied to all the images of regular users, to
prevent malicious FR systems from acquiring their identity information. In this
work, we discover the optimization dilemma in the existing methods -- the local
optima problem in large-batch optimization and the gradient information
elimination problem in small-batch optimization. To solve these problems, we
propose Gradient Accumulation (GA) to aggregate multiple small-batch gradients
into a one-step iterative gradient to enhance the gradient stability and reduce
the usage of quantization operations. Experiments show that our proposed method
achieves high performance on the Privacy-Commons dataset against black-box face
recognition models.
Related papers
- Sparsity-Preserving Differentially Private Training of Large Embedding
Models [67.29926605156788]
DP-SGD is a training algorithm that combines differential privacy with gradient descent.
Applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency.
We present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.
arXiv Detail & Related papers (2023-11-14T17:59:51Z) - DP-SGD with weight clipping [1.0878040851638]
We present a novel approach that mitigates the bias arising from traditional gradient clipping.
By leveraging a public upper bound of the Lipschitz value of the current model and its current location within the search domain, we can achieve refined noise level adjustments.
arXiv Detail & Related papers (2023-10-27T09:17:15Z) - Dynamic Privacy Allocation for Locally Differentially Private Federated
Learning with Composite Objectives [10.528569272279999]
This paper proposes a differentially private federated learning algorithm for strongly convex but possibly nonsmooth problems.
The proposed algorithm adds artificial noise to the shared information to ensure privacy and dynamically allocates the time-varying noise variance to minimize an upper bound of the optimization error.
Numerical results show the superiority of the proposed algorithm over state-of-the-art methods.
arXiv Detail & Related papers (2023-08-02T13:30:33Z) - FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
FedLAP-DP is a novel privacy-preserving approach for federated learning.
A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes.
Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
arXiv Detail & Related papers (2023-02-02T12:56:46Z) - Differentially Private Stochastic Gradient Descent with Low-Noise [49.981789906200035]
Modern machine learning algorithms aim to extract fine-grained information from data to provide accurate predictions, which often conflicts with the goal of privacy protection.
This paper addresses the practical and theoretical importance of developing privacy-preserving machine learning algorithms that ensure good performance while preserving privacy.
arXiv Detail & Related papers (2022-09-09T08:54:13Z) - OPOM: Customized Invisible Cloak towards Face Privacy Protection [58.07786010689529]
We investigate the face privacy protection from a technology standpoint based on a new type of customized cloak.
We propose a new method, named one person one mask (OPOM), to generate person-specific (class-wise) universal masks.
The effectiveness of the proposed method is evaluated on both common and celebrity datasets.
arXiv Detail & Related papers (2022-05-24T11:29:37Z) - Auditing Privacy Defenses in Federated Learning via Generative Gradient
Leakage [9.83989883339971]
Federated Learning (FL) framework brings privacy benefits to distributed learning systems.
Recent studies have revealed that private information can still be leaked through shared information.
We propose a new type of leakage, i.e., Generative Gradient Leakage (GGL)
arXiv Detail & Related papers (2022-03-29T15:59:59Z) - Federated Learning for Face Recognition with Gradient Correction [52.896286647898386]
In this work, we introduce a framework, FedGC, to tackle federated learning for face recognition.
We show that FedGC constitutes a valid loss function similar to standard softmax.
arXiv Detail & Related papers (2021-12-14T09:19:29Z) - Local Differential Privacy for Bayesian Optimization [12.05395706770007]
We consider a black-box optimization in the nonparametric Gaussian process setting with local differential privacy (LDP) guarantee.
Specifically, the rewards from each user are further corrupted to protect privacy and the learner only has access to the corrupted rewards to minimize the regret.
We present three almost optimal algorithms based on the GP-UCB framework and Laplace DP mechanism.
arXiv Detail & Related papers (2020-10-13T21:50:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.