A Defense against Adversarial Examples via Image Squeezing

Feature-filter: Detecting adversarial examples by filtering out recessive features

Many companies offer automatic speech recognition or Speech-to-Text APIs for use in diverse applications. However, audio classification algorithms trained with deep neural networks (DNNs) can sometimes misclassify adversarial examples, posing a significant threat to critical applications. In this paper, we present a novel way to create adversarial audio examples using a genetic algorithm. Our algorithm creates adversarial examples by iteratively adding perturbations to the original audio signal. Unlike most white-box adversarial example generations, our approach does not require knowledge about the target DNN's model and parameters (black-box) and heavy computational power of GPU resources. To show the feasibility of the proposed idea, we implement a tool called, Foolgle, using a genetic algorithm that performs untargeted attacks to create adversarial audio examples and evaluate those with the state-of-the-art Google Cloud Speech-to-Text API. Our preliminary experiment results show that Foolgle deceives the API with a success probability of 86%.

Adversarial examples are crucial tools for assessing the robustness of deep neural networks (DNNs) and revealing potential security vulnerabilities. Adversarial example generation methods based on Generative Adversarial Networks (GANs) have made significant progress in generating image adversarial examples, but still suffer from insufficient sparsity and transferability. To address these issues, this study proposes a novel semi-white-box untargeted adversarial example generation method named Wavelet-AdvGAN, with an explicit threat model defined as follows. Specifically, the attack is strictly untargeted without predefined target categories, aiming solely to mislead DNNs into classifying adversarial examples into any category other than the original label. It adopts a semi-white-box setting where attackers are denied access to the target model’s private information. Regarding the generator’s information dependence, the training phase only utilizes public resources (i.e., the target model’s public architecture and CIFAR-10 public training data), while the test phase generates adversarial examples through one-step feedforward of clean images without interacting with the target model. The method incorporates a Frequency Sub-band Difference (FSD) module and a Wavelet Transform Local Feature (WTLF) extraction module, evaluating the differences between original and adversarial examples from the frequency domain perspective. This approach constrains the magnitude of perturbations, reinforces feature regions, and further enhances the attack effectiveness, thereby improving the sparsity and transferability of adversarial examples. Experimental results demonstrate that the Wavelet-AdvGAN method achieves an average increase of 1.26% in attack success rates under two defense strategies—data augmentation and adversarial training. Additionally, the adversarial transferability improves by an average of 2.7%. Moreover, the proposed method exhibits a lower l0 norm, indicating better perturbation sparsity. Consequently, it effectively evaluates the robustness of deep neural networks.

State-of-the-art Deep Neural Networks (DNNs) are promoting medical image processing. However, DNNs are susceptible to adversarial attacks, which could significantly deteriorate model performances and pose a threat to clinical diagnoses. One common method for prevention is through adversarial training, which is highly dependent on harnessing adversarial examples during the training stage. However, adversarial medical examples generated by many existing works are too perceptible to be adversarial examples. To improve the imperceptibility, we proposed a Regional Saliency Map Attack that generates an adversarial example by only perturbing a small number of pixels. Extensive experiments have shown that, on average, our method caused the same degradation in model performance by quantitatively less perceptible perturbations. Visualisations have also verified that the improvement in imperceptibility in an image is both global and regional.

Deep neural networks (DNNs) have useful applications in machine learning tasks involving recognition and pattern analysis. Despite the favorable applications of DNNs, these systems can be exploited by adversarial examples. An adversarial example, which is created by adding a small amount of noise to an original sample, can cause misclassification by the DNN. Under specific circumstances, it may be necessary to create a selective untargeted adversarial example that will not be classified as certain avoided classes. Such is the case, for example, if a modified tank cover can cause misclassification by a DNN, but the bandit equipped with the DNN must misclassify the modified tank as a class other than certain avoided classes, such as a tank, armored vehicle, or self-propelled gun. That is, selective untargeted adversarial examples are needed that will not be perceived as certain classes, such as tanks, armored vehicles, or self-propelled guns. In this study, we propose a selective untargeted adversarial example that exhibits 100% attack success with minimum distortions. The proposed scheme creates a selective untargeted adversarial example that will not be classified as certain avoided classes while minimizing distortions in the original sample. To generate untargeted adversarial examples, a transformation is performed to minimize the probability of certain avoided classes and distortions in the original sample. As experimental datasets, we used MNIST and CIFAR-10, including the Tensorflow library. The experimental results demonstrate that the proposed scheme creates a selective untargeted adversarial example that exhibits 100% attack success with minimum distortions (1.325 and 34.762 for MNIST and CIFAR-10, respectively).

The automatic speech recognition (ASR) system based on deep neural network is easy to be attacked by an adversarial example due to the vulnerability of neural network, which is a hot topic in recent years. The adversarial example does harm to the ASR system, especially if the common-dependent ASR goes wrong, it will lead to serious consequences. To improve the robustness and security of the ASR system, the defense method against adversarial examples must be proposed. Based on this idea, we propose an algorithm of devastation and detection on adversarial examples which can attack the current advanced ASR system. We choose advanced text-dependent and command-dependent ASR system as our target system. Generating adversarial examples by the OPT on text-dependent ASR and the GA-based algorithm on command-dependent ASR. The main idea of our method is input transformation of the adversarial examples. Different random intensities and kinds of noise are added to the adversarial examples to devastate the perturbation previously added to the normal examples. From the experimental results, the method performs well. For the devastation of examples, the original speech similarity before and after adding noise can reach 99.68%, the similarity of the adversarial examples can reach 0%, and the detection rate of the adversarial examples can reach 94%.

Deep neural networks (DNNs) provide superior performance on machine learning tasks such as image recognition, speech recognition, pattern analysis, and intrusion detection. However, an adversarial example, created by adding a little noise to an original sample, can cause misclassification by a DNN. This is a serious threat to the DNN because the added noise is not detected by the human eye. For example, if an attacker modifies a right-turn sign so that it misleads to the left, autonomous vehicles with the DNN will incorrectly classify the modified sign as pointing to the left, but a person will correctly classify the modified sign as pointing to the right. Studies are under way to defend against such adversarial examples. The existing method of defense against adversarial examples requires an additional process such as changing the classifier or modifying input data. In this paper, we propose a new method for detecting adversarial examples that does not invoke any additional process. The proposed scheme can detect adversarial examples by using a pattern feature of the classification scores of adversarial examples. We used MNIST and CIFAR10 as experimental datasets and Tensorflow as a machine learning library. The experimental results show that the proposed method can detect adversarial examples with success rates: 99.05% and 99.9% for the untargeted and targeted cases in MNIST, respectively, and 94.7% and 95.8% for the untargeted and targeted cases in CIFAR10, respectively.

Deep Neural Networks (DNN) have strong capabilities of memories, feature identifications and automatic analyses, solving various complex problems. However, DNN classifiers have obvious fragility that adding several unnoticeable perturbations to the original examples will lead to the errors in the classifier identification. In the field of communications, the adversarial examples will greatly reduce the accuracy of the signal identification, causing great information security risks. Considering the adversarial examples pose a serious threat to the security of the DNN models, studying their generation mechanisms and testing their attack effects are critical to ensuring the information security of the communication networks. This paper will study the generation of the adversarial examples and the influences of the adversarial examples on the accuracy of the DNN-based communication signal identification. Meanwhile, this paper will study the influences of the adversarial examples under the white-box models and black-box models, and explore the adversarial attack influences of the factors such as perturbation levels and iterative steps. The insights of this study would be helpful for ensuring the security of information networks and designing robust DNN communication networks.

Deep neural networks, which can learn the representative and discriminative features from data in a hierarchical manner, have achieved state-of-the-art performance in the remote sensing scene classification task. Despite the great success that deep learning algorithms have obtained, their vulnerability toward adversarial examples deserves our special attention. In this article, we systematically analyze the threat of adversarial examples on deep neural networks for remote sensing scene classification. Both targeted and untargeted attacks are performed to generate subtle adversarial perturbations, which are imperceptible to a human observer but may easily fool the deep learning models. Simply adding these perturbations to the original high-resolution remote sensing (HRRS) images, adversarial examples can be generated, and there are only slight differences between the adversarial examples and the original ones. An intriguing discovery in our study shows that most of these adversarial examples may be misclassified into the wrong category by the state-of-the-art deep neural networks with very high confidence. This phenomenon, undoubtedly, may limit the practical deployment of these deep learning models in the safety-critical remote sensing field. To address this problem, the adversarial training strategy is further investigated in this article, which significantly increases the resistibility of deep models toward adversarial examples. Extensive experiments on three benchmark HRRS image data sets demonstrate that while most of the well-known deep neural networks are sensitive to adversarial perturbations, the adversarial training strategy helps to alleviate their vulnerability toward adversarial examples.

The recent success of brain-inspired deep neural networks (DNNs) in solving complex, high-level visual tasks has led to rising expectations for their potential to match the human visual system. However, DNNs exhibit idiosyncrasies that suggest their visual representation and processing might be substantially different from human vision. One limitation of DNNs is that they are vulnerable to adversarial examples, input images on which subtle, carefully designed noises are added to fool a machine classifier. The robustness of the human visual system against adversarial examples is potentially of great importance as it could uncover a key mechanistic feature that machine vision is yet to incorporate. In this study, we compare the visual representations of white- and black-box adversarial examples in DNNs and humans by leveraging functional magnetic resonance imaging (fMRI). We find a small but significant difference in representation patterns for different (i.e. white- versus black- box) types of adversarial examples for both humans and DNNs. However, human performance on categorical judgment is not degraded by noise regardless of the type unlike DNN. These results suggest that adversarial examples may be differentially represented in the human visual system, but unable to affect the perceptual experience.

Deep neural networks (DNNs), which learn a hierarchical representation of features, have shown remarkable performance in big data analytics of remote sensing. However, previous research indicates that DNNs are easily spoofed by adversarial examples, which are crafted images with artificial perturbations that fool DNN models toward wrong predictions. To comprehensively evaluate the impact of adversarial examples on the remote sensing image (RSI) scene classification, this study tests eight state-of-the-art classification DNNs on six RSI benchmarks. These data sets include both optical and synthetic-aperture radar (SAR) images of different spectral and spatial resolutions. In the experiment, we create 48 classification scenarios and use four cutting-edge attack algorithms to investigate the influence of the adversarial example on the classification of RSIs. The experimental result shows that the fooling rates of the attacks are all over 98% across the 48 scenarios. We also find that, for the optical data, the seriousness of the adversarial problem has a negative relationship with the richness of the feature information. Besides, adversarial examples generated from SAR images are used easily for fooling the models with an average fooling rate of 76.01%. By analyzing the class distribution of these adversarial examples, we find that the distribution of the misclassifications is not affected by the types of models and attack algorithms-adversarial examples of RSIs of the same class cluster on fixed several classes. The analysis of classes of adversarial examples not only helps us explore the relationships between data set classes but also provides insights for further designing defensive algorithms.

The widespread application of deep neural network (DNN) techniques is being challenged by adversarial examples—the legitimate input added with imperceptible and well-designed perturbation that can fool DNNs easily in the DNN testing/deploying stage. Previous white-box adversarial example generation algorithms used the Jacobian gradient information to add the perturbation. This imprecise and inexplicit information can cause unnecessary perturbation when generating adversarial examples. This paper aims to address this issue. We first propose to apply the more informative and distilled gradient information, namely, integrated gradient, to generate adversarial examples. To further make the perturbation more imperceptible, we propose to employ the restriction combination of L 0 and L 1 / L 2 second, which can restrict the total perturbation and the perturbation points simultaneously. Meanwhile, to address the nondifferentiable problem of L 1 , we explore a proximal operation of L 1 third. On the basis of these three works, we propose two Integrated gradient-based White-box Adversarial example generation algorithms (IWA): Integrated gradient-based Finite Point Attack (IFPA) and Integrated gradient-based Universe Attack (IUA). IFPA is suitable for situations where there are a determined number of points to be perturbed. IUA is suitable for situations where no perturbation point number is preset to obtain more adversarial examples. We verify the effectiveness of the proposed algorithms on both structured and unstructured data sets, and compare them with five baseline generation algorithms. The results show that our proposed algorithms craft adversarial examples with more imperceptible perturbation and satisfactory crafting rate. L 2 restriction is suitable for unstructured data sets and L 1 restriction performs better in the structured data set.

Deep neural networks (DNNs) have gained widespread adoption in computer vision. Unfortunately, state-of-the-art DNNs are vulnerable to adversarial example (AE) attacks, where an adversary introduces imperceptible perturbations to a test example for defrauding DNNs. The obstacles have urged intensive research on improving the DNN robustness via adversarial training, that is, the clean data set is blended with adversarial examples to carry out training. However, the adversarial example attack technologies are open-ended, and the adversarial training is insufficient to focus on improving robustness performance. To circumvent this limitation, we mitigate adversarial example attacks from another perspective, which aims at detecting adversarial examples. Feature autoencoder detector (FADetector), a novel defense framework that exploits feature knowledge is proposed. One of the hallmarks of FADetector is to not involve adversarial examples to train the detector. Our extensive evaluation on MNIST and CIFAR-10 data sets demonstrates that our defense outperforms the conventional autoencoder detectors in terms of detection accuracy.

Deep learning models have shown their great capability for the hyperspectral image (HSI) classification task in recent years. Nevertheless, their vulnerability towards adversarial attacks could not be neglected. In this study, we systematically analyze the influence of adversarial attacks on the HSI classification task for the first time. While existing research of adversarial attacks focuses on the generation of adversarial examples in the RGB domain, the experiments in this study show such adversarial examples could also exist in the hyperspectral domain. Although the difference between the generated adversarial image and the original hyperspectral data is imperceptible to the human visual system, most of the existing state-of-the-art deep learning models could be fooled by the adversarial image to make wrong predictions. To address this challenge, a novel self-attention context network (SACNet) is further proposed. We discover that the global context information contained in HSI can significantly improve the robustness of deep neural networks when confronted with adversarial attacks. Extensive experiments on three benchmark HSI datasets demonstrate that the proposed SACNet possesses stronger resistibility towards adversarial examples compared with the existing state-of-the-art deep learning models.

Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While adversarial examples are well studied in classification tasks, other learning problems may have different properties. For instance, semantic segmentation requires additional components such as dilated convolutions and multiscale processing. In this paper, we aim to characterize adversarial examples based on spatial context information in semantic segmentation. We observe that spatial consistency information can be potentially leveraged to detect adversarial examples robustly even when a strong adaptive attacker has access to the model and detection strategies. We also show that adversarial examples based on attacks considered within the paper barely transfer among models, even though transferability is common in classification. Our observations shed new light on developing adversarial attacks and defenses to better understand the vulnerabilities of DNNs.