Deep Adversarial Learning Research Articles

Retraction Notice: A Modified Balancing Approach for Renewable Based Microgrids Using Deep Adversarial Learning

Retraction Notice: A Modified Balancing Approach for Renewable Based Microgrids Using Deep Adversarial Learning

Destabilizing Attack and Robust Defense for Inverter-Based Microgrids by Adversarial Deep Reinforcement Learning

The droop controllers of inverter-based resources (IBRs) can be adjustable by grid operators to facilitate regulation services. Considering the increasing integration of IBRs at power distribution level systems like microgrids, cyber security is becoming a major concern. This paper investigates the data-driven destabilizing attack and robust defense strategy based on adversarial deep reinforcement learning for inverter-based microgrids. Firstly, the full-order high-fidelity model and reduced-order small-signal model of typical inverter-based microgrids are recapitulated. Then the destabilizing attack on the droop control gains is analyzed, which reveals its impact on system small-signal stability. Finally, the attack and defense problems are formulated as Markov decision process (MDP) and adversarial MDP (AMDP). The problems are solved by twin delayed deep deterministic policy gradient (TD3) algorithm to find the least effort attack path of the system and obtain the corresponding robust defense strategy. The simulation studies are conducted in an inverter-based microgrid system with 4 IBRs and IEEE 123-bus system with 10 IBRs to evaluate the proposed method.

Image Composition Method Based on a Spatial Position Analysis Network

Realistic image composition aims to composite new images by fusing a source object into a target image. It is a challenging problem due to the complex multi-task framework, including sensible object placement, appearance consistency, shadow generation, etc. Most existing researchers attempt to address one of the issues. Especially before compositing, there is no matching assignment between the source object and target image, which often leads to unreasonable results. To address the issues above, we consider image composition as an image generation problem and propose a deep adversarial learning network via spatial position analysis. We target the analysis network segment and classify the objects in target images. A spatial alignment network matches the segmented objects with the source objects, and predicts a sensible placement position, and an adversarial network generates a realistic composite image with the shadow and reflection of the source object. Furthermore, we use the classification information of target objects to filter out unreasonable image compositing. Moreover, we introduce a new test set to evaluate the network generalization for our multi-task image composition dataset. Extensive experimental results of the SHU (Shanghai University) dataset demonstrate that our deep spatial position analysis network remarkably enhances the compositing performance in realistic, shadow, and reflection generations.

Adversarial Deep Learning based Dampster–Shafer data fusion model for intelligent transportation system

Intelligent Transportation Systems (ITS) have revolutionized transportation by incorporating advanced technologies for efficient and safe mobility. However, these systems face challenges ensuring security and resilience against adversarial attacks. This research addresses these challenges and introduces a novel Dampster–Shafer data fusion-based Adversarial Deep Learning (DS-ADL) Model for ITS in fog cloud environments. Our proposed model focuses on three levels of adversarial attacks: original image level, feature level, and decision level. Adversarial examples are generated at each level to evaluate the system’s vulnerability comprehensively. To enhance the system’s capabilities, we leverage the power of several vital components. Firstly, we employ Dempster–Shafer-based Multimodal Sensor Fusion, enabling the fusion of information from multiple sensors for improved scene understanding. This fusion approach enhances the system’s perception and decision-making abilities. For feature extraction and classification, we utilize ResNet 101, a deep learning architecture known for its effectiveness in computer vision tasks. We introduced a novel Monomodal Multidimensional Gaussian Model (MMGM-DD) based Adversarial Detection approach to detect adversarial examples. This detection mechanism enhances the system’s ability to identify and mitigate adversarial attacks in real-time. Additionally, we incorporate the Defensive Distillation method for adversarial training, which trains the model to be robust against attacks by exposing it to adversarial examples during the training process. To evaluate the performance of our proposed model, we utilize two datasets: Google Speech Command version 0.01 and the German Traffic Sign Recognition Benchmark (GTSRB). Evaluation metrics include latency delay and computation time (fog–cloud), accuracy, MSE, loss, and F-score for attack detection and defense. The results and discussions demonstrate the effectiveness of our Dampster–Shafer data fusion-based Adversarial Deep Learning Model in enhancing the robustness and security of ITS in fog–cloud environments. The model’s ability to detect and defend against adversarial attacks while maintaining low-latency fog–cloud operations highlights its potential for real-world deployment in ITS.

Adversarial Deep Learning in Anomaly based Intrusion Detection Systems for IoT Environments

Adversarial Deep Learning in Anomaly based Intrusion Detection Systems for IoT Environments

Defect-aware Super-resolution Thermography by Adversarial Learning

Infrared thermography is a valuable non-destructive tool for inspection of materials. It measures the surface temperature evolution, from which hidden defects may be detected. Yet, thermal cameras typically have a low native spatial resolution resulting in a blurry and low-quality thermal image sequence and videos. In this study, a novel adversarial deep learning framework, called Dual-IRT-GAN, is proposed for performing super-resolution tasks. The proposed Dual-IRT-GAN attempts to achieve the objective of improving local texture details, as well as highlighting defective regions. The generated high-resolution images are then delivered to the discriminator for adversarial training using GAN's framework. The proposed Dual-IRT-GAN model, which is trained on an exclusive virtual dataset, is demonstrated on experimental thermographic data obtained from fibre reinforced polymers having a variety of defect types, sizes, and depths. The obtained results show its high performance in maintaining background colour consistency and removing undesired noise, and in highlighting defect zones with finer detailed textures in highresolution.

MR image restoration and segmentation via denoising deep adversarial network for blood vessels accurate diagnosis

Segmenting the hepatic and portal veins is a difficult task, since it has multiple distortions. For effective restoration and to minimize distortions, a multi-stage deep adversarial learning network was proposed. The proposed network provides high reliability in segmenting hepatic and portal veins from distorted Magnetic Resonance (MR) images. The Proposed network directly considers the variation in vascular flow for vessel segmentation. By a two-stage deep adversarial network, which consist of geometric distortion by regularization in the first stage and in the second stage image blurriness is adjusted by a sub-pixel mechanism. To detect the hepatic venous flow, shared clustering was used to correlate the hepatic flow and venous flow. To have better image segmentation by restoration, end-to-end training by image adaptive by denoising was employed. The proposed Denoising Deep Adversarial Network (DDAN) generalizability is shown by curating a distorted TCGA dataset. We perform experiments by segmenting the distorted MR image with estimating depth, semantic interclass decision, and classification. The proposed DDAN is evaluated on a multi-phase open MRI public dataset from a local clinic and Kaggle Br35H. The obtained quantitative and qualitative evaluation data shows the practical applicability of the proposed deep learning model. We observed that the image edges, portal, and hepatic vein scale texture are clearly segmented to assist real-time applications like tumour surgery.

Interpreting Universal Adversarial Example Attacks on Image Classification Models

Mitigating adversarial deep learning attacks remains challenging, partly because of the ease and low cost in carrying out such attacks. Therefore, in this paper, we focus on the understanding of universal adversarial example attack on image classification models. Specifically, we seek to understand the difference(s) between adversarial examples in two adversarial datasets (DAmageNet and PGD dataset) and clean examples in ImageNet learned by the classification model, and whether we can use such findings to resist adversarial example attacks. We also seek to determine if we can retrain a discriminator to discriminate whether the input image is an adversarial example, using adversarial training. We then design a number of experiments (e.g., class activation map (CAM) analysis, feature map analysis, feature maps/filters changing, adversarial training, and binary classification model) to help us determine whether the universal adversarial dataset can be successfully used to attack the classification model. This, in turn, contributes to a better understanding of adversarial defenses over pretrained classification model from an interpretation perspective. To the best of our knowledge, this work is one of the earliest works to systematically investigate the interpretation of universal adversarial example attack on image classification models, both visually and quantitatively.

Attacking Spectrum Sensing With Adversarial Deep Learning in Cognitive Radio-Enabled Internet of Things

Attacking Spectrum Sensing With Adversarial Deep Learning in Cognitive Radio-Enabled Internet of Things

Gearbox compound fault diagnosis method based on deep adversarial graph convolution transfer learning network under low label ratios

Advancement in measurement techniques has dramatically contributed to the development of the modern manufacturing industry. As the primary fault causing unplanned downtime of mechanical equipment, gearbox compound faults are usually coupled by single faults with unequal severity and are difficult to obtain. In industrial scenarios, monitoring data for extreme operating conditions is not available in advance, and labeling samples is time-consuming and costly. However, current research on unseen compound fault diagnosis relies on numerous labeled samples to train the model, and few studies are conducted on transfer learning and unseen compound fault diagnosis under low label ratios. To address the issue, a gearbox compound fault diagnosis method based on deep adversarial graph convolution transfer learning network (DAGCTLN) under low label ratios is proposed. Specifically, a novel DAGCTLN model, including a feature extractor, two label classifiers, and a discriminator, is constructed to realize the diagnosis of faults in the transfer domain and unseen compound faults in the source and target domains. The feature extractor of a three-layer graph convolutional network is presented to achieve deep extraction of fault features under low label ratios. Then a domain space adversarial mechanism between the feature extractor and discriminator is used to achieve global alignment of the source and target domain features. Furthermore, two label classifiers are constructed, and the adversarial adaptation of the decision boundary is realized by maxi-min the classifier difference to achieve subdomain alignment of the same class features in all domains. Experimental results indicate that DAGCTLN can achieve the highest fault diagnosis accuracy in the transfer domain compared to state-of-the-art algorithms. The average diagnosis accuracy of compound faults in all domains can reach 98.41% even if the label ratio is only 0.1, which provides guiding significance for the safe operation and predictive maintenance of mechanical equipment.

Deep Adversarial Reinforcement Learning based Incentive Mechanism for Content Delivery in D2D-Enabled Mobile Networks

With the explosive growth of mobile devices at the edge of mobile networks, the amount of content that needs to be transmitted is exploded. As it takes resources (cache, bandwidth, and power) for the edge server and nearby devices to deliver content, the incentive mechanism with the optimal pricing and content delivery strategy needs to be studied without relying on the knowledge of network parameters in a competitive environment. In this paper, built on the framework of content delivery with the Stackelberg game, we have proposed a robust deep reinforcement learning method based on adversarial training to learn price strategy for lack of knowledge of private information. Specifically, the Stackelberg game is constructed to describe the interaction between different service providers and service demanders, and a deep adversarial reinforcement learning method is proposed to approximate the opponent’s decision in the worst case, where the price strategy can be trained end-to-end in the competitive environment. The simulation results show that the proposed algorithm can form an effective price strategy and improve the utility of service providers.

An intelligent recommendation method based on multi-interest network and adversarial deep learning

Recommender systems have shown to popular in many Internet communities, as they could help users discover interesting items based on their history behaviors. However, with the explosive growth of data-intensive tasks and online information, cybersecurity risks become larger, conventional collaborative recommendation algorithms may not meet users’ security requirements. Besides, the sparsity issue and the cold-start issue also hinder the performance of conventional recommendation methods. Recently, deep learning has shown to outperform traditional modeling techniques, which can be employed in Recommender systems (RSs) to improve user behavior prediction. In light of these challenges and observations, an intelligent recommendation method based on multi-interest network and adversarial deep learning is proposed, where multi-source behavior information is applied for multi-view embedding extraction for better prediction performance. Specifically, multi-view preference embeddings, including self-embedding, interaction-aware embedding, and neighbor-based embedding, are combined to model users’ interests at a finer granularity. Besides, in neighbor-based embedding learning, an adversarial search scheme is adopted for fast similarity searching and privacy preservation. Finally, a DNN-based prediction mechanism is adopted for embedding aggregation and final prediction. Extensive experiments on real-world datasets show that our proposal achieves decent prediction performance with security concerns compared with state-of the-art baselines.

Unpaired deep adversarial learning for multi-class segmentation of instruments in robot-assisted surgical videos.

Image segmentation of instruments in the raw surgical videos is a critical component of intraoperative assistance softwares. Challenges include addressing rendered overlays occluding the instrument while providing pivotal input to instrument tracking frameworks and, train the segmentation process with limited labelled data available from surgical videos. The proposed adversarial network, InstruSegNet uses unpaired training (eliminating need for massive paired data) for automated multi-class surgical instrument segmentation in raw surgical videos with complex backgrounds. The proposed method is applied for single/multiple robotic and rigid instruments and optimised on least square Generative Adversarial Networks loss. Promising validation has been conducted on the publicly available dataset. Proposed approach for multi-class segmentation of robotic and rigid instruments meets outstanding performance in terms of accuracy and surpasses the existing methods. This work facilitates segmenting instrument information without manual interventions from raw videos providing means to code surgeon's actions for developing intelligent assistance software.

Multi-site diagnostic classification of Autism spectrum disorder using adversarial deep learning on resting-state fMRI

Existing imaging studies in Autism spectrum disorder (ASD) mainly focused on single-site resting-state functional magnetic resonance imaging (rs-fMRI) data, which may contain limited samples and suffer from geographic bias. The lack of effective detection in information mining of rs-fMRI is a main reason for affecting the recognition rate of multi-site diagnostic. This study aims to propose a two-stage adversarial learning model with sliding window that integrates information from multi-site rs-fMRI data at the cost of minimal information loss. First, single rs-fMRI data is sampled with a sliding window to preserve both the spatial and temporal information of original data. And then, site-shared features of these samples are extracted through an adversarial learning model. Finally, the model is fine-tuned to learn discriminative disease-related features. Experimental results show that through adversarial learning, the heterogeneity problem among multi-site data is solved. Furthermore, the spatial–temporal information on rs-fMRI is effectively extracted and yields better classification performance (0.80 accuracy, 0.81 sensitivity, 0.80 specificity) than the state-of-the-art methods. Our results demonstrate the feasibility of the proposed method in the ASD classification task and the importance of fully exploiting the site-shared and spatial–temporal information in rs-fMRI data for multi-site ASD study.

Regularized adversarial learning for normalization of multi-batch untargeted metabolomics data.

Untargeted metabolomics by mass spectrometry is the method of choice for unbiased analysis of molecules in complex samples of biological, clinical or environmental relevance. The exceptional versatility and sensitivity of modern high-resolution instruments allows profiling of thousands of known and unknown molecules in parallel. Inter-batch differences constitute a common and unresolved problem in untargeted metabolomics, and hinder the analysis of multi-batch studies or the intercomparison of experiments. We present a new method, Regularized Adversarial Learning Preserving Similarity (RALPS), for the normalization of multi-batch untargeted metabolomics data. RALPS builds on deep adversarial learning with a three-term loss function that mitigates batch effects while preserving biological identity, spectral properties and coefficients of variation. Using two large metabolomics datasets, we showcase the superior performance of RALPS as compared with six state-of-the-art methods for batch correction. Further, we demonstrate that RALPS scales well, is robust, deals with missing values and can handle different experimental designs. https://github.com/zamboni-lab/RALPS. Supplementary data are available at Bioinformatics online.

Deep Adversarial Reinforcement Learning Method to Generate Control Policies Robust Against Worst-Case Value Predictions

Deep Adversarial Reinforcement Learning Method to Generate Control Policies Robust Against Worst-Case Value Predictions

Controllable Wireless Spoofing Attack Based on Conditional BEGAN and Auxiliary Channel Sensing

This paper investigates how to build a controllable wireless spoofing attack launch framework that is driven by fundamental channel modeling and practical wireless datasets. First, we propose a wireless spoofing attack scheme against the defense mechanism with adversarial deep learning. To obtain channel characteristics and facilitate offline training of the attack model, auxiliary channel sensing is proposed with fundamental channel modeling. Based on these, a conditional boundary equilibrium generative adversarial network (CBEGAN) is designed with adversarial autoencoder (AAE), which takes true labels of signals and channel characteristics as conditions and enables the generation of controllable spoofing signals to fool the protected legitimate classifier. We verify the performance of the proposed spoofing attack scheme with CBEGAN and channel sensing by using wireless datasets, which contain signal data of multiple emitters and modulation types. Results show that the proposed scheme outperforms random attack, replay attack, and the recent attack scheme based on generative adversarial network (GAN) when a single legitimate emitter sends a fixed modulation type. It is also shown that the average attack success probability of the proposed CBEGAN attack model can reach more than 80% while mimicking multiple emitters and modulation types. The performance of the proposed scheme on different channel conditions including signal-to-noise ratio (SNR) and K-factor of the Rician fading channel is evaluated.

Deep adversarial learning system for fault diagnosis in fused deposition modeling with imbalanced data

Fused deposition modeling (FDM) has been widely promoted as an emerging additive manufacturing technology. With the growing demand for its commercialization, the requirements for the quality of products are increasing. Quality control and fault diagnosis in the manufacturing process are becoming prominent. However, most research focuses on monitoring the process, while few studies diagnose the faults to find their causes, especially concerning the drift of process parameters. The domain-shifting problem occurs when process parameters drift in FDM process and it largely influences the diagnosis performance of a trained model. To fill this gap, this paper proposes a deep adversarial learning system for fault diagnosis in the FDM process, based on captured upper layer images during the manufacturing process. Conditional generative adversarial network is adopted to augment the original dataset and solve the between-class data imbalance problem. As for domain-shifting problems, this research utilizes a domain adversarial neural network to process features from different domains, so as to identify the process parameters with drifting values in the FDM process. A laboratory case ablation study verifies the effectiveness and accuracy of the proposed method in diagnosing.

Undersampling artifact reduction for free-breathing 3D stack-of-radial MRI based on a deep adversarial learning network

PurposeStack-of-radial MRI allows free-breathing abdominal scans, however, it requires relatively long acquisition time. Undersampling reduces scan time but can cause streaking artifacts and degrade image quality. This study developed deep learning networks with adversarial loss and evaluated the performance of reducing streaking artifacts and preserving perceptual image sharpness. MethodsA 3D generative adversarial network (GAN) was developed for reducing streaking artifacts in stack-of-radial abdominal scans. Training and validation datasets were self-gated to 5 respiratory states to reduce motion artifacts and to effectively augment the data. The network used a combination of three loss functions to constrain the anatomy and preserve image quality: adversarial loss, mean-squared-error loss and structural similarity index loss. The performance of the network was investigated for 3–5 times undersampled data from 2 institutions. The performance of the GAN for 5 times accelerated images was compared with a 3D U-Net and evaluated using quantitative NMSE, SSIM and region of interest (ROI) measurements as well as qualitative scores of radiologists. ResultsThe 3D GAN showed similar NMSE (0.0657 vs. 0.0559, p = 0.5217) and significantly higher SSIM (0.841 vs. 0.798, p < 0.0001) compared to U-Net. ROI analysis showed GAN removed streaks in both the background air and the tissue and was not significantly different from the reference mean and variations. Radiologists' scores showed GAN had a significant improvement of 1.6 point (p = 0.004) on a 4-point scale in streaking score while no significant difference in sharpness score compared to the input. Conclusion3D GAN removes streaking artifacts and preserves perceptual image details.

Adversarial deep evolutionary learning for drug design

The design of a new therapeutic agent is a time-consuming and expensive process. The rise of machine intelligence provides a grand opportunity of expeditiously discovering novel drug candidates through smart search in the vast molecular structural space. In this paper, we propose a new approach called adversarial deep evolutionary learning (ADEL) to search for novel molecules in the latent space of an adversarial generative model and keep improving the latent representation space. In ADEL, a custom-made adversarial autoencoder (AAE) model is developed and trained under a deep evolutionary learning (DEL) process. This involves an initial training of the AAE model, followed by an integration of multi-objective evolutionary optimization in the continuous latent representation space of the AAE rather than the discrete structural space of molecules. By using the AAE, an arbitrary distribution can be provided to the training of AAE such that the latent representation space is set to that distribution. This allows for a starting latent space from which new samples can be produced. Throughout the process of learning, new samples of high quality are generated after each iteration of training and then added back into the full dataset, therefore, allowing for a more comprehensive procedure of understanding the data structure. This combination of evolving data and continuous learning not only enables improvement in the generative model, but the data as well. By comparing ADEL to the previous work in DEL, we see that ADEL can obtain better property distributions. We show that ADEL is able to design high-quality molecular structures which can be further used for virtual and experimental screenings.