Adversarial attack method against image classification based on haze perturbation

In recent years, with the widespread application of Vision Transformer (ViT) in visual trackers, their robustness has received increasing attention. However, by focusing on global interactions between image patches, ViT reduces sensitivity to local noise, posing new challenges for adversarial attacks. Meanwhile, existing decision-based adversarial attack methods often overlook the differences in noise sensitivity between different patches, further limiting the compression efficiency of adversarial noise, especially in ViT. In visual tracking, existing adversarial attack methods primarily target Siamese network-based trackers, and research on adversarial attacks against Transformer-based trackers, particularly decision-based black-box attacks, is still relatively limited. To implement effective black-box attacks on Transformer-based trackers, this paper innovatively proposes patch-based adversarial noise compression (PANC), a decision-based adversarial attack method. This method effectively compresses adversarial noise patch by patch, significantly improving compression efficiency and attack concealment. PANC also introduces a noise sensitivity matrix that dynamically adds and reduces adversarial noise, optimizing the spatial distribution of noise while decreasing the number of queries. We validated the effectiveness of the proposed PANC attack method on several Transformer-based trackers, including OSTrack, STARK, TransT, and MixformerV2, and three public large-scale benchmark datasets: GOT-10k, TrackingNet, and LaSOT. Experimental results show that compared to the existing state-of-the-art adversarial attack method, the IoU attack, PANC compresses the noise level to 10%, improving the attack effectiveness by 162% with the number of queries of only 45.7%. Furthermore, PANC can serve as an initialization or post-processing optimization strategy for other adversarial attack methods, providing a more flexible and efficient mechanism for adversarial example generation. Our work reveals the vulnerabilities of existing Transformer-based visual trackers and offers new ideas for further improving the efficiency and concealment of adversarial attacks.

With the continuous development of deep learning in the field of Synthetic Aperture Radar (SAR) image processing, it is found that image recognition is vulnerable to interference and the accuracy is greatly reduced. Therefore, if a general adversarial attack method is designed to generate adversarial examples(AEs) capable of deceiving different types of convolutional neural network models, it can protect target images from being correctly recognized by adversaries and safeguard image privacy information. However, most of the current adversarial attack methods have too large attack scope and interference intensity, and do not have the ability to universally attack different neural network models, resulting in poor concealment, deception, and transfer deception of adversarial attacks. In this paper, we propose a general Key Points Sparse Attack (KPSA) method for SAR images, which achieves excellent deception and transfer deception while controlling the attack range and jamming strength. It is a general and efficient adversarial attack method. KPSA uses the generator to generate intensity interference images and imposes amplitude constraint, uses the key points extraction method to generate position interference images to realize sparse attack, uses the difference value(d-value) loss function to achieve fast convergence of the training model, and achieves transfer deception performance without depending on the type of discriminator. The deception rate and transfer deception rate experiments were conducted on MSTAR and ATRNet-STAR. By comparing with the advanced methods in the field of adversarial attacks, it was verified that the KPSA method is superior to the current advanced methods, and it was confirmed that the KPSA method has application value in various complex practical scenarios.

The challenge of classifying multimodal remote sensing images has garnered significant interest in light of the growing diversity of remote sensing image data modalities. Current studies primarily concentrate on increasing the classification task’s accuracy by improving the fusion strategy or incorporating auxiliary architectures. However, there is currently a lack of research in the area of adversarial attack for multimodal remote sensing image classification models as compared to the study of unimodal classification models. To overcome this issue, our research firstly investigates the adversarial robustness of multimodal remote sensing image classification under different fusion strategies, which adopts the improved classical adversarial attack methods to test the adversarial robustness of multimodal remote sensing image classification model architectures with three different fusion strategies; Then a new multimodal adversarial attack method is proposed for the multimodal model, which adopts balanced perturbation loss and cooperative adversarial loss, in which the balanced perturbation loss is used to balance the level of perturbation of different modalities, and the cooperative adversarial loss is used to reduce the conflict of different modality perturbations on the classification result. By combining balanced perturbation loss and cooperative adversarial loss to attack multimodal models, the cooperation between modalities is continuously optimized.Finally, the study demonstrates the weak adversarial robustness of the multimodal remote sensing image classification model, which robustness is easily influenced by the fusion strategies and the attack methods. Additionally, a better attack effect is obtained by the multimodal multiloss cooperative adversarial attack method proposed in this paper.

Adversarial examples are one of the largest vulnerability of deep neural networks. An attacker can deceive the classifiers easily with the malicious inputs (called adversarial examples), which perturbations are slightly added to benign inputs. Various attack methods have been studied in both white-box and black-box settings, and some methods achieve high attack success rates even in the black-box settings; that is, the attacker is restricted to only query accesses to the target network. In this paper, we propose a simple hyperparameter-free score-based black-box \(\ell _\infty \)-adversarial attack using local uniform noises and a random search. Specifically, we construct adversarial perturbations by combining local uniform noises such as vertical-wise and horizontal-wise, and incorporate this idea into the random search method to update the perturbation sequentially. We evaluate our method in terms of attack success rates and query efficiency using models that classify common datasets CIFAR-10 and ImageNet. We show that our method achieves higher attack success rates and query efficiency than previous attack methods, especially in low-query budgets on both untargeted and targeted attack settings. We also examine attacks to adversarially trained models and discuss the effect of local uniform noises on these models. Furthermore, we show that our method achieves relatively high attack success rates and query efficiency on average against input-transformation-based defense methods, and is virtually unaffected by these defense methods.KeywordsBlack-box adversarial attacksAI security

Multivariate time series forecasting plays an increasingly critical role in various applications, such as power management, smart cities, finance, and healthcare. Recent advances in temporal graph neural networks (GNNs) have shown promising results in multivariate time series forecasting due to their ability to characterize high-dimensional nonlinear correlations and temporal patterns. However, the vulnerability of deep neural networks (DNNs) constitutes serious concerns about using these models to make decisions in real-world applications. Currently, how to defend multivariate forecasting models, especially temporal GNNs, is overlooked. The existing adversarial defense studies are mostly in static and single-instance classification domains, which cannot apply to forecasting due to the generalization challenge and the contradiction issue. To bridge this gap, we propose an adversarial danger identification method for temporally dynamic graphs to effectively protect GNN-based forecasting models. Our method consists of three steps: 1) a hybrid GNN-based classifier to identify dangerous times; 2) approximate linear error propagation to identify the dangerous variates based on the high-dimensional linearity of DNNs; and 3) a scatter filter controlled by the two identification processes to reform time series with reduced feature erasure. Our experiments, including four adversarial attack methods and four state-of-the-art forecasting models, demonstrate the effectiveness of the proposed method in defending forecasting models against adversarial attacks.

Recently, adversarial attacks have shown to lead the state-of-the-art deep neural networks (DNNs) to misclassification. However, most adversarial attacks are generated according to whether they are perceptual to human visual system, measured by geometric metrics such as the l2-norm, which ignores the common watermarks in cyber-physical systems. In this paper, we propose a fast adversarial watermark attack (FAWA) method based on fast differential evolution technique, which optimally superimposes a watermark on an image to fool DNNs. We also attempt to explain the reason why the attack is successful and propose two hypotheses on the vulnerability of DNN classifiers and the influence of the watermark attack on higher-layer features extraction respectively. In addition, we propose two countermeasure methods against FAWA based on random rotation and median filtering respectively. Experimental results show that our method achieves 41.3% success rate in fooling VGG-16 and have good transferability. Our approach is also shown to be effective in deceiving deep learning as a service (DLaaS) systems as well as the physical world. The proposed FAWA, hypotheses, and the countermeasure methods, provide a timely help for DNN designers to gain some knowledge of model vulnerability while designing DNN classifiers and related DLaaS applications.

The goal of textual adversarial attack methods is to replace some words in an input text in order to make the victim model misbehave. This article proposes an effective word-level adversarial attack method based on sememes and an improved quantum-behaved particle swarm optimization (QPSO) algorithm. The sememe-based substitute method, which uses the words sharing the same sememes as the substitutes of the original words, is first employed to form the reduced search space. Then, an improved QPSO algorithm, called historical information-guided QPSO with random drift local attractor (HIQPSO-RD), is proposed to search the reduced search space for adversarial examples. The HIQPSO-RD introduces historical information into the current mean best position of the QPSO, for the purpose of improving the convergence speed of the algorithm, by enhancing its exploration ability and preventing the premature convergence of the swarm. The proposed algorithm uses the random drift local attractor technique to make a good balance between its exploration and exploitation, so that the algorithm can find a better adversarial attack example with low grammaticality and perplexity (PPL). In addition, it employs a two-stage diversity control strategy to enhance the search performance of the algorithm. Experiments on three natural language processing (NLP) datasets, with three commonly used nature language processing models as victim models, show that our method achieves higher attack success rates but lower modification rates than the state-of-the-art adversarial attack methods. Moreover, the results of human evaluations show that adversarial examples generated by our method can better maintain the semantic similarity and grammatical correctness of the original input.

Masking and purifying inputs for blocking textual adversarial attacks

DiffProtect: Generative adversarial examples using diffusion models for facial privacy protection

Adversarial attacks have exposed serious vulnerabilities in deep neural networks (DNNs), causing misclassifications through human-imperceptible perturbations to DNN inputs. We explore a new direction in the field of adversarial attacks by suggesting attacks that aim to degrade the energy or latency of DNNs rather than their classification accuracy. As a specific embodiment of this new threat vector, we propose and demonstrate adversarial sparsity attacks, which modify a DNN's inputs so as to reduce sparsity (or the incidence of zeros) in its internal activation values. Exploiting sparsity in hardware and software has emerged as a popular approach to improve DNN efficiency in resource-constrained systems. The proposed attack, therefore, increases the execution time and energy consumption of sparsity-optimized DNN implementations, raising concern over their deployment in latency and energy-critical applications. We propose a systematic methodology to generate adversarial inputs for sparsity attacks by formulating an objective function that quantifies the network's activation sparsity and minimizing this function using iterative gradient-descent techniques. To prevent easy detection of the attack, we further ensure that the perturbation magnitude is within a specified constraint and that the perturbation does not affect classification accuracy. We launch both white-box and black-box versions of adversarial sparsity attacks on image recognition DNNs and demonstrate that they decrease activation sparsity by 1.16×-1.82×. On a sparsity-optimized DNN accelerator, the attack results in degradations of 1.12×-1.59× in latency and 1.18×-1.99× in energy-delay product (EDP). Additionally, we analyze the impact of various hyperparameters and constraints on the attack's efficacy. Finally, we evaluate defense techniques, such as activation thresholding and input quantization and demonstrate that the proposed attack is able to withstand them, highlighting the need for further efforts in this new direction within the field of adversarial machine learning.

Deep Neural Networks (DNNs) are very vulnerable to adversarial attacks because of the instability and unreliability under the training process. Recently, many studies about adversarial patches have been conducted that aims to misclassify the image classifier model by attaching patches to images. However, most of the previous research employs adversarial patches that are visible to human vision, making them easy to be identified and responded to. In this paper, we propose a new method entitled Spatially Localized Perturbation GAN (SLP-GAN) that can generate visually natural patches while maintaining a high attack success rate. SLP-GAN utilizes a spatially localized perturbation taken from the most representative area of target images (i.e., attention map) as the adversarial patches. The patch region is extracted using the Grad-CAM algorithm to improve the attacking ability against the target model. Our experiment, tested on GTSRB and CIFAR-10 datasets, shows that SLP-GAN outperforms the state-of-the-art adversarial patch attack methods in terms of visual fidelity.

Adversarial examples: A survey of attacks and defenses in deep learning-enabled cybersecurity systems

Deep learning has revolutionized image recognition. One significant obstacle still remains, the vulnerability of these models to adversarial attacks. These attacks manipulate images with subtle changes that cause CNN misclassification. While methods, such as adversarial training, have been proposed to defend against adversarial attacks, they incur additional training costs, either extra input samples or auxiliary models. In this work, we propose an efficient approach to deploying robust models that utilize image transformations to remove adversarial noises. We investigate the performance of simple transformations and report several effective ones, including Affine blur, Gaussian blur, Median blur, and Bilateral blur against various adversarial attack methods, such as Fast Gradient Sign Method (FGSM), Randomized + FGSM (RFGSM), and Projected Gradient Descent (PGD). We apply these image transformation techniques to the widely used ImageNet dataset, and experimental results demonstrate the potential of image transformation methods as a strong defense against adversarial attacks in deep learning-based image classification systems, especially when combined with cutting-edge neural network architectures such as ResNet50 and DenseNet121. Our comprehensive results show that these transformations can significantly improve the robustness of CNN models against adversarial attacks on ImageNet, achieving a recovery rate of up to 85% to 90% without incurring extra resource costs.

With the continuous development of wireless communication and artificial intelligence technology, Internet of Things (IoT) technology has made great progress. Deep learning methods are currently used in IoT technology, but deep neural networks (DNNs) are notoriously susceptible to adversarial examples, and subtle pixel changes to images can result in incorrect recognition results from DNNs. In the real‐world application, the patches generated by the recent physical attack methods are larger or less realistic and easily detectable. To address this problem, a Generative Adversarial Network based on Visual attention model and Style transfer network (GAN‐VS) is proposed, which reduces the patch area and makes the patch more natural and less noticeable. A visual attention model combined with generative adversarial network is introduced to detect the critical regions of image recognition, and only generate patches within the critical regions to reduce patch area and improve attack efficiency. For any type of seed patch, an adversarial patch can be generated with a high degree of stylistic and content similarity to the attacked image by generative adversarial network and style transfer network. Experimental evaluation shows that the proposed GAN‐VS has good camouflage and outperforms state‐of‐the‐art adversarial patch attack methods.

More and more security situation awareness strategies in power network use deep learning as the data processing method. However, the endogenous security problem of deep learning poses a challenge to the robustness required for power network security situation awareness, and gives attackers an opportunity to add small perturbation to the network and fail the security situation awareness strategy. In this paper, we build the deep neural networks for the power network dataset. We verify a variety of adversarial example attack methods against deep neural networks, and tested the success rate of attacks on different types of networks to compare the difference of attack methods and target model. We can see from the experiment results that adversarial example attacks can have a great impact on the power network security situation awareness and pose a threat to the power network.