Mingfu Xue

Yushu Zhang, Nuo Chen, Shuren Qi et al.

Image forensics, aiming to ensure the authenticity of the image, has made great progress in dealing with common image manipulation such as copy-move, splicing, and inpainting in the past decades. However, only a few researchers pay attention to an emerging editing technique called image recoloring, which can manipulate the color values of an image to give it a new style. To prevent it from being used maliciously, the previous approaches address the conventional recoloring from the perspective of inter-channel correlation and illumination consistency. In this paper, we try to explore a solution from the perspective of the spatial correlation, which exhibits the generic detection capability for both conventional and deep learning-based recoloring. Through theoretical and numerical analysis, we find that the recoloring operation will inevitably destroy the spatial correlation between pixels, implying a new prior of statistical discriminability. Based on such fact, we generate a set of spatial correlation features and learn the informative representation from the set via a convolutional neural network. To train our network, we use three recoloring methods to generate a large-scale and high-quality data set. Extensive experimental results in two recoloring scenes demonstrate that the spatial correlation features are highly discriminative. Our method achieves the state-of-the-art detection accuracy on multiple benchmark datasets and exhibits well generalization for unknown types of recoloring methods.

Mingfu Xue, Xin Wang, Yinghao Wu et al.

Intellectual property (IP) protection for Deep Neural Networks (DNNs) has raised serious concerns in recent years. Most existing works embed watermarks in the DNN model for IP protection, which need to modify the model and lack of interpretability. In this paper, for the first time, we propose an interpretable intellectual property protection method for DNN based on explainable artificial intelligence. Compared with existing works, the proposed method does not modify the DNN model, and the decision of the ownership verification is interpretable. We extract the intrinsic features of the DNN model by using Deep Taylor Decomposition. Since the intrinsic feature is composed of unique interpretation of the model's decision, the intrinsic feature can be regarded as fingerprint of the model. If the fingerprint of a suspected model is the same as the original model, the suspected model is considered as a pirated model. Experimental results demonstrate that the fingerprints can be successfully used to verify the ownership of the model and the test accuracy of the model is not affected. Furthermore, the proposed method is robust to fine-tuning attack, pruning attack, watermark overwriting attack, and adaptive attack.

Mingfu Xue, Leo Yu Zhang, Yushu Zhang et al.

The intellectual property protection of deep learning (DL) models has attracted increasing serious concerns. Many works on intellectual property protection for Deep Neural Networks (DNN) models have been proposed. The vast majority of existing work uses DNN watermarking to verify the ownership of the model after piracy occurs, which is referred to as passive verification. On the contrary, we focus on a new type of intellectual property protection method named active copyright protection, which refers to active authorization control and user identity management of the DNN model. As of now, there is relatively limited research in the field of active DNN copyright protection. In this review, we attempt to clearly elaborate on the connotation, attributes, and requirements of active DNN copyright protection, provide evaluation methods and metrics for active copyright protection, review and analyze existing work on active DL model intellectual property protection, discuss potential attacks that active DL model copyright protection techniques may face, and provide challenges and future directions for active DL model intellectual property protection. This review is helpful to systematically introduce the new field of active DNN copyright protection and provide reference and foundation for subsequent work.

Qiantao Yang, Liquan Chen, Mingfu Xue et al.

Federated learning has drawn widespread interest from researchers, yet the data heterogeneity across edge clients remains a key challenge, often degrading model performance. Existing methods enhance model compatibility with data heterogeneity by splitting models and knowledge distillation. However, they neglect the insufficient communication bandwidth and computing power on the client, failing to strike an effective balance between addressing data heterogeneity and accommodating limited client resources. To tackle this limitation, we propose a personalized federated learning method based on cosine sparsification parameter packing and dual-weighted aggregation (FedCSPACK), which effectively leverages the limited client resources and reduces the impact of data heterogeneity on model performance. In FedCSPACK, the client packages model parameters and selects the most contributing parameter packages for sharing based on cosine similarity, effectively reducing bandwidth requirements. The client then generates a mask matrix anchored to the shared parameter package to improve the alignment and aggregation efficiency of sparse updates on the server. Furthermore, directional and distribution distance weights are embedded in the mask to implement a weighted-guided aggregation mechanism, enhancing the robustness and generalization performance of the global model. Extensive experiments across four datasets using ten state-of-the-art methods demonstrate that FedCSPACK effectively improves communication and computational efficiency while maintaining high model accuracy.

Mingfu Xue, Shifeng Ni, Yinghao Wu et al.

Recent researches demonstrate that Deep Neural Networks (DNN) models are vulnerable to backdoor attacks. The backdoored DNN model will behave maliciously when images containing backdoor triggers arrive. To date, existing backdoor attacks are single-trigger and single-target attacks, and the triggers of most existing backdoor attacks are obvious thus are easy to be detected or noticed. In this paper, we propose a novel imperceptible and multi-channel backdoor attack against Deep Neural Networks by exploiting Discrete Cosine Transform (DCT) steganography. Based on the proposed backdoor attack method, we implement two variants of backdoor attacks, i.e., N-to-N backdoor attack and N-to-One backdoor attack. Specifically, for a colored image, we utilize DCT steganography to construct the trigger on different channels of the image. As a result, the trigger is stealthy and natural. Based on the proposed method, we implement multi-target and multi-trigger backdoor attacks. Experimental results demonstrate that the average attack success rate of the N-to-N backdoor attack is 93.95% on CIFAR-10 dataset and 91.55% on TinyImageNet dataset, respectively. The average attack success rate of N-to-One attack is 90.22% and 89.53% on CIFAR-10 and TinyImageNet datasets, respectively. Meanwhile, the proposed backdoor attack does not affect the classification accuracy of the DNN model. Moreover, the proposed attack is demonstrated to be robust to the state-of-the-art backdoor defense (Neural Cleanse).

Mingfu Xue, Xin Wang, Shichang Sun et al.

In recent years, many backdoor attacks based on training data poisoning have been proposed. However, in practice, those backdoor attacks are vulnerable to image compressions. When backdoor instances are compressed, the feature of specific backdoor trigger will be destroyed, which could result in the backdoor attack performance deteriorating. In this paper, we propose a compression-resistant backdoor attack based on feature consistency training. To the best of our knowledge, this is the first backdoor attack that is robust to image compressions. First, both backdoor images and their compressed versions are input into the deep neural network (DNN) for training. Then, the feature of each image is extracted by internal layers of the DNN. Next, the feature difference between backdoor images and their compressed versions are minimized. As a result, the DNN treats the feature of compressed images as the feature of backdoor images in feature space. After training, the backdoor attack against DNN is robust to image compression. Furthermore, we consider three different image compressions (i.e., JPEG, JPEG2000, WEBP) in feature consistency training, so that the backdoor attack is robust to multiple image compression algorithms. Experimental results demonstrate the effectiveness and robustness of the proposed backdoor attack. When the backdoor instances are compressed, the attack success rate of common backdoor attack is lower than 10%, while the attack success rate of our compression-resistant backdoor is greater than 97%. The compression-resistant attack is still robust even when the backdoor images are compressed with low compression quality. In addition, extensive experiments have demonstrated that, our compression-resistant backdoor attack has the generalization ability to resist image compression which is not used in the training process.

Mingfu Xue, Yinghao Wu, Yushu Zhang et al.

Training high performance Deep Neural Networks (DNNs) models require large-scale and high-quality datasets. The expensive cost of collecting and annotating large-scale datasets make the valuable datasets can be considered as the Intellectual Property (IP) of the dataset owner. To date, almost all the copyright protection schemes for deep learning focus on the copyright protection of models, while the copyright protection of the dataset is rarely studied. In this paper, we propose a novel method to actively protect the dataset from being used to train DNN models without authorization. Experimental results on on CIFAR-10 and TinyImageNet datasets demonstrate the effectiveness of the proposed method. Compared with the model trained on clean dataset, the proposed method can effectively make the test accuracy of the unauthorized model trained on protected dataset drop from 86.21% to 38.23% and from 74.00% to 16.20% on CIFAR-10 and TinyImageNet datasets, respectively.

Haoqi Wang, Mingfu Xue, Shichang Sun et al.

Deep neural networks (DNN) have achieved remarkable performance in various fields. However, training a DNN model from scratch requires a lot of computing resources and training data. It is difficult for most individual users to obtain such computing resources and training data. Model copyright infringement is an emerging problem in recent years. For instance, pre-trained models may be stolen or abuse by illegal users without the authorization of the model owner. Recently, many works on protecting the intellectual property of DNN models have been proposed. In these works, embedding watermarks into DNN based on backdoor is one of the widely used methods. However, when the DNN model is stolen, the backdoor-based watermark may face the risk of being detected and removed by an adversary. In this paper, we propose a scheme to detect and remove watermark in deep neural networks via generative adversarial networks (GAN). We demonstrate that the backdoor-based DNN watermarks are vulnerable to the proposed GAN-based watermark removal attack. The proposed attack method includes two phases. In the first phase, we use the GAN and few clean images to detect and reverse the watermark in the DNN model. In the second phase, we fine-tune the watermarked DNN based on the reversed backdoor images. Experimental evaluations on the MNIST and CIFAR10 datasets demonstrate that, the proposed method can effectively remove about 98% of the watermark in DNN models, as the watermark retention rate reduces from 100% to less than 2% after applying the proposed attack. In the meantime, the proposed attack hardly affects the model's performance. The test accuracy of the watermarked DNN on the MNIST and the CIFAR10 datasets drops by less than 1% and 3%, respectively.

Mingfu Xue, Yinghao Wu, Zhiyu Wu et al.

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack information such as the trigger size, which is difficult to satisfy in realistic scenarios. In this paper, a novel backdoor detection method based on adversarial examples is proposed. The proposed method leverages intentional adversarial perturbations to detect whether an image contains a trigger, which can be applied in both the training stage and the inference stage (sanitize the training set in training stage and detect the backdoor instances in inference stage). Specifically, given an untrusted image, the adversarial perturbation is added to the image intentionally. If the prediction of the model on the perturbed image is consistent with that on the unperturbed image, the input image will be considered as a backdoor instance. Compared with most existing defense works, the proposed adversarial perturbation based method requires low computational resources and maintains the visual quality of the images. Experimental results show that, the backdoor detection rate of the proposed defense method is 99.63%, 99.76% and 99.91% on Fashion-MNIST, CIFAR-10 and GTSRB datasets, respectively. Besides, the proposed method maintains the visual quality of the image as the l2 norm of the added perturbation are as low as 2.8715, 3.0513 and 2.4362 on Fashion-MNIST, CIFAR-10 and GTSRB datasets, respectively. In addition, it is also demonstrated that the proposed method can achieve high defense performance against backdoor attacks under different attack settings (trigger transparency, trigger size and trigger pattern). Compared with the existing defense work (STRIP), the proposed method has better detection performance on all the three datasets, and is more efficient than STRIP.

Mingfu Xue, Zhiyu Wu, Jian Wang et al.

A well-trained DNN model can be regarded as an intellectual property (IP) of the model owner. To date, many DNN IP protection methods have been proposed, but most of them are watermarking based verification methods where model owners can only verify their ownership passively after the copyright of DNN models has been infringed. In this paper, we propose an effective framework to actively protect the DNN IP from infringement. Specifically, we encrypt the DNN model's parameters by perturbing them with well-crafted adversarial perturbations. With the encrypted parameters, the accuracy of the DNN model drops significantly, which can prevent malicious infringers from using the model. After the encryption, the positions of encrypted parameters and the values of the added adversarial perturbations form a secret key. Authorized user can use the secret key to decrypt the model. Compared with the watermarking methods which only passively verify the ownership after the infringement occurs, the proposed method can prevent infringement in advance. Moreover, compared with most of the existing active DNN IP protection methods, the proposed method does not require additional training process of the model, which introduces low computational overhead. Experimental results show that, after the encryption, the test accuracy of the model drops by 80.65%, 81.16%, and 87.91% on Fashion-MNIST, CIFAR-10, and GTSRB, respectively. Moreover, the proposed method only needs to encrypt an extremely low number of parameters, and the proportion of the encrypted parameters of all the model's parameters is as low as 0.000205%. The experimental results also indicate that, the proposed method is robust against model fine-tuning attack and model pruning attack. Moreover, for the adaptive attack where attackers know the detailed steps of the proposed method, the proposed method is also demonstrated to be robust.

Shichang Sun, Mingfu Xue, Jian Wang et al.

Recently, the research on protecting the intellectual properties (IP) of deep neural networks (DNN) has attracted serious concerns. A number of DNN copyright protection methods have been proposed. However, most of the existing watermarking methods focus on verifying the copyright of the model, which do not support the authentication and management of users' fingerprints, thus can not satisfy the requirements of commercial copyright protection. In addition, the query modification attack which was proposed recently can invalidate most of the existing backdoor-based watermarking methods. To address these challenges, in this paper, we propose a method to protect the intellectual properties of DNN models by using an additional class and steganographic images. Specifically, we use a set of watermark key samples to embed an additional class into the DNN, so that the watermarked DNN will classify the watermark key sample as the predefined additional class in the copyright verification stage. We adopt the least significant bit (LSB) image steganography to embed users' fingerprints into watermark key images. Each user will be assigned with a unique fingerprint image so that the user's identity can be authenticated later. Experimental results demonstrate that, the proposed method can protect the copyright of DNN models effectively. On Fashion-MNIST and CIFAR-10 datasets, the proposed method can obtain 100% watermark accuracy and 100% fingerprint authentication success rate. In addition, the proposed method is demonstrated to be robust to the model fine-tuning attack, model pruning attack, and the query modification attack. Compared with three existing watermarking methods (the logo-based, noise-based, and adversarial frontier stitching watermarking methods), the proposed method has better performance on watermark accuracy and robustness against the query modification attack.

Mingfu Xue, Can He, Shichang Sun et al.

Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, and trigger the malicious behaviors by submitting specific backdoor instance. However, almost all the existing backdoor works focused on the digital domain, while few studies investigate the backdoor attacks in real physical world. Restricted to a variety of physical constraints, the performance of backdoor attacks in the real physical world will be severely degraded. In this paper, we propose a robust physical backdoor attack method, PTB (physical transformations for backdoors), to implement the backdoor attacks against deep learning models in the real physical world. Specifically, in the training phase, we perform a series of physical transformations on these injected backdoor instances at each round of model training, so as to simulate various transformations that a backdoor may experience in real world, thus improves its physical robustness. Experimental results on the state-of-the-art face recognition model show that, compared with the backdoor methods that without PTB, the proposed attack method can significantly improve the performance of backdoor attacks in real physical world. Under various complex physical conditions, by injecting only a very small ratio (0.5%) of backdoor instances, the attack success rate of physical backdoor attacks with the PTB method on VGGFace is 82%, while the attack success rate of backdoor attacks without the proposed PTB method is lower than 11%. Meanwhile, the normal performance of the target DNN model has not been affected.

Mingfu Xue, Shichang Sun, Can He et al.

The training of Deep Neural Networks (DNN) is costly, thus DNN can be considered as the intellectual properties (IP) of model owners. To date, most of the existing protection works focus on verifying the ownership after the DNN model is stolen, which cannot resist piracy in advance. To this end, we propose an active DNN IP protection method based on adversarial examples against DNN piracy, named ActiveGuard. ActiveGuard aims to achieve authorization control and users' fingerprints management through adversarial examples, and can provide ownership verification. Specifically, ActiveGuard exploits the elaborate adversarial examples as users' fingerprints to distinguish authorized users from unauthorized users. Legitimate users can enter fingerprints into DNN for identity authentication and authorized usage, while unauthorized users will obtain poor model performance due to an additional control layer. In addition, ActiveGuard enables the model owner to embed a watermark into the weights of DNN. When the DNN is illegally pirated, the model owner can extract the embedded watermark and perform ownership verification. Experimental results show that, for authorized users, the test accuracy of LeNet-5 and Wide Residual Network (WRN) models are 99.15% and 91.46%, respectively, while for unauthorized users, the test accuracy of the two DNNs are only 8.92% (LeNet-5) and 10% (WRN), respectively. Besides, each authorized user can pass the fingerprint authentication with a high success rate (up to 100%). For ownership verification, the embedded watermark can be successfully extracted, while the normal performance of the DNN model will not be affected. Further, ActiveGuard is demonstrated to be robust against fingerprint forgery attack, model fine-tuning attack and pruning attack.

Mingfu Xue, Can He, Zhiyu Wu et al.

In this paper, we propose a novel physical stealth attack against the person detectors in real world. The proposed method generates an adversarial patch, and prints it on real clothes to make a three dimensional (3D) invisible cloak. Anyone wearing the cloak can evade the detection of person detectors and achieve stealth. We consider the impacts of those 3D physical constraints (i.e., radian, wrinkle, occlusion, angle, etc.) on person stealth attacks, and propose 3D transformations to generate 3D invisible cloak. We launch the person stealth attacks in 3D physical space instead of 2D plane by printing the adversarial patches on real clothes under challenging and complex 3D physical scenarios. The conventional and 3D transformations are performed on the patch during its optimization process. Further, we study how to generate the optimal 3D invisible cloak. Specifically, we explore how to choose input images with specific shapes and colors to generate the optimal 3D invisible cloak. Besides, after successfully making the object detector misjudge the person as other objects, we explore how to make a person completely disappeared, i.e., the person will not be detected as any objects. Finally, we present a systematic evaluation framework to methodically evaluate the performance of the proposed attack in digital domain and physical world. Experimental results in various indoor and outdoor physical scenarios show that, the proposed person stealth attack method is robust and effective even under those complex and challenging physical conditions, such as the cloak is wrinkled, obscured, curved, and from different angles. The attack success rate in digital domain (Inria data set) is 86.56%, while the static and dynamic stealth attack performance in physical world is 100% and 77%, respectively, which are significantly better than existing works.

Mingfu Xue, Chengxiang Yuan, Can He et al.

Recently, the membership inference attack poses a serious threat to the privacy of confidential training data of machine learning models. This paper proposes a novel adversarial example based privacy-preserving technique (AEPPT), which adds the crafted adversarial perturbations to the prediction of the target model to mislead the adversary's membership inference model. The added adversarial perturbations do not affect the accuracy of target model, but can prevent the adversary from inferring whether a specific data is in the training set of the target model. Since AEPPT only modifies the original output of the target model, the proposed method is general and does not require modifying or retraining the target model. Experimental results show that the proposed method can reduce the inference accuracy and precision of the membership inference model to 50%, which is close to a random guess. Further, for those adaptive attacks where the adversary knows the defense mechanism, the proposed AEPPT is also demonstrated to be effective. Compared with the state-of-the-art defense methods, the proposed defense can significantly degrade the accuracy and precision of membership inference attacks to 50% (i.e., the same as a random guess) while the performance and utility of the target model will not be affected.

Mingfu Xue, Chengxiang Yuan, Can He et al.

In this paper, we propose a natural and robust physical adversarial example attack method targeting object detectors under real-world conditions. The generated adversarial examples are robust to various physical constraints and visually look similar to the original images, thus these adversarial examples are natural to humans and will not cause any suspicions. First, to ensure the robustness of the adversarial examples in real-world conditions, the proposed method exploits different image transformation functions, to simulate various physical changes during the iterative optimization of the adversarial examples generation. Second, to construct natural adversarial examples, the proposed method uses an adaptive mask to constrain the area and intensities of the added perturbations, and utilizes the real-world perturbation score (RPS) to make the perturbations be similar to those real noises in physical world. Compared with existing studies, our generated adversarial examples can achieve a high success rate with less conspicuous perturbations. Experimental results demonstrate that, the generated adversarial examples are robust under various indoor and outdoor physical conditions, including different distances, angles, illuminations, and photographing. Specifically, the attack success rate of generated adversarial examples indoors and outdoors is high up to 73.33% and 82.22%, respectively. Meanwhile, the proposed method ensures the naturalness of the generated adversarial example, and the size of added perturbations is much smaller than the perturbations in the existing works. Further, the proposed physical adversarial attack method can be transferred from the white-box models to other object detection models.

Mingfu Xue, Yushu Zhang, Jian Wang et al.

The training and creation of deep learning model is usually costly, thus it can be regarded as an intellectual property (IP) of the model creator. However, malicious users who obtain high-performance models may illegally copy, redistribute, or abuse the models without permission. To deal with such security threats, a few deep neural networks (DNN) IP protection methods have been proposed in recent years. This paper attempts to provide a review of the existing DNN IP protection works and also an outlook. First, we propose the first taxonomy for DNN IP protection methods in terms of six attributes: scenario, mechanism, capacity, type, function, and target models. Then, we present a survey on existing DNN IP protection works in terms of the above six attributes, especially focusing on the challenges these methods face, whether these methods can provide proactive protection, and their resistances to different levels of attacks. After that, we analyze the potential attacks on DNN IP protection methods from the aspects of model modifications, evasion attacks, and active attacks. Besides, a systematic evaluation method for DNN IP protection methods with respect to basic functional metrics, attack-resistance metrics, and customized metrics for different application scenarios is given. Lastly, future research opportunities and challenges on DNN IP protection are presented.

Mingfu Xue, Shichang Sun, Zhiyu Wu et al.

The popularity of various social platforms has prompted more people to share their routine photos online. However, undesirable privacy leakages occur due to such online photo sharing behaviors. Advanced deep neural network (DNN) based object detectors can easily steal users' personal information exposed in shared photos. In this paper, we propose a novel adversarial example based privacy-preserving technique for social images against object detectors based privacy stealing. Specifically, we develop an Object Disappearance Algorithm to craft two kinds of adversarial social images. One can hide all objects in the social images from being detected by an object detector, and the other can make the customized sensitive objects be incorrectly classified by the object detector. The Object Disappearance Algorithm constructs perturbation on a clean social image. After being injected with the perturbation, the social image can easily fool the object detector, while its visual quality will not be degraded. We use two metrics, privacy-preserving success rate and privacy leakage rate, to evaluate the effectiveness of the proposed method. Experimental results show that, the proposed method can effectively protect the privacy of social images. The privacy-preserving success rates of the proposed method on MS-COCO and PASCAL VOC 2007 datasets are high up to 96.1% and 99.3%, respectively, and the privacy leakage rates on these two datasets are as low as 0.57% and 0.07%, respectively. In addition, compared with existing image processing methods (low brightness, noise, blur, mosaic and JPEG compression), the proposed method can achieve much better performance in privacy protection and image visual quality maintenance.