Evaluating Impact of Image Transformations on Adversarial Examples

With the widespread use of deep learning models in various applications. People are gradually realizing the vulnerability of these models to adversarial attacks. Adversarial training is an effective strategy to defend against adversarial attacks. Based on the advantages and disadvantages of the current mainstream Fast Gradient Sign Method (FGSM) adversarial training and Projected Gradient Descent (PGD) adversarial training, this paper proposes a hybrid adversarial training that integrates FGSM and PGD methods and uses the ResNet-18 model and SVHN dataset for testing. Experimental results show that hybrid adversarial training can effectively reduce training time. Its accuracy on the original data set is higher than that of PGD adversarial training, which is improved by about 2%. The performance when facing FGSM attacks is almost the same as that of single FGSM adversarial training. The performance when facing PGD attacks decreases more significantly, which is about 2% to 3% lower than that of PGD adversarial training. This study not only helps to understand the robustness of hybrid adversarial training to models facing adversarial attacks but also helps in studying new adversarial training strategies.

Deep learning, particularly convolutional neural networks (CNNs), has proven valuable for brain tumor classification, aiding diagnostic and therapeutic decisions in medical imaging. Despite their accuracy, these models are vulnerable to adversarial attacks, compromising their reliability in clinical settings. In this research, we utilized a VGG16-based CNN model to classify brain tumors, achieving 96% accuracy on clean magnetic resonance imaging (MRI) data. To assess robustness, we exposed the model to Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks, which reduced accuracy to 32% and 13%, respectively. We then applied a multi-layered defense strategy, including adversarial training with FGSM and PGD examples and feature squeezing techniques such as bit-depth reduction and Gaussian blurring. This approach improved model resilience, achieving 54% accuracy on FGSM and 47% on PGD adversarial examples. Our results highlight the importance of proactive defense strategies for maintaining the reliability of AI in medical imaging under adversarial conditions.

Untargeted white-box adversarial attack with heuristic defence methods in real-time deep learning based network intrusion detection system

The design of a security scheme for beamforming prediction is critical for next-generation wireless networks (5G, 6G, and beyond). However, there is no consensus about protecting beamforming prediction using deep learning algorithms in these networks. This paper presents the security vulnerabilities in deep learning for beamforming prediction using deep neural networks in 6G wireless networks, which treats the beamforming prediction as a multi-output regression problem. It is indicated that the initial DNN model is vulnerable to adversarial attacks, such as Fast Gradient Sign Method , Basic Iterative Method , Projected Gradient Descent , and Momentum Iterative Method , because the initial DNN model is sensitive to the perturbations of the adversarial samples of the training data. This study offers two mitigation methods, such as adversarial training and defensive distillation, for adversarial attacks against artificial intelligence-based models used in the millimeter-wave (mmWave) beamforming prediction. Furthermore, the proposed scheme can be used in situations where the data are corrupted due to the adversarial examples in the training data. Experimental results show that the proposed methods defend the DNN models against adversarial attacks in next-generation wireless networks.

Smart city applications that request sensitive user information necessitate a comprehensive data privacy solution. Federated learning (FL), also known as privacy by design, is a new paradigm in machine learning (ML). However, FL models are susceptible to adversarial attacks, similar to other AI models. In this paper, we propose federated adversarial training (FAT) strategies to generate robust global models that are resistant to adversarial attacks. We apply two adversarial attack methods, projected gradient descent (PGD) and the fast gradient sign method (FGSM), to our air pollution dataset to generate adversarial samples. We then evaluate the effectiveness of our FAT strategies in defending against these attacks. Our experiments show that FGSM-based adversarial attacks have a negligible impact on the accuracy of global models, while PGD-based attacks are more effective. However, we also show that our FAT strategies can make global models robust enough to withstand even PGD-based attacks. For example, the accuracy of our FAT-PGD and FL-mixed-PGD models is 81.13% and 82.60%, respectively, compared to 91.34% for the baseline FL model. This represents a reduction in accuracy of 10%, but this could be potentially mitigated by using a more complex and larger model. Our results demonstrate that FAT can enhance the security and privacy of sustainable smart city applications. We also show that it is possible to train robust global models from modest datasets per client, which challenges the conventional wisdom that adversarial training requires massive datasets.

Deep neural networks, despite their remarkable performance on image classification tasks, remain critically vulnerable to adversarial examples — imperceptibly perturbed inputs engineered to induce misclassification. In this paper, we propose and evaluate a dual-layer defense framework against adversarial attacks on image classifiers trained on the ImageNet1K Mini dataset. Our approach combines a convolutional autoencoder as a preprocessing denoising step with a ResNet-50 classifier augmented by a novel block-switching mechanism to disrupt adversarial gradient signal. We evaluate the system under Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks across a range of perturbation budgets ε ∈ {0.01, 0.02, 0.03, 0.05, 0.07, 0.10}. Our defense recovers +23.08% accuracy against FGSM and +54.44% against PGD on in-distribution data, and achieves 100% full recovery on an out- of-distribution generalisation test (83.3% baseline). We further employ Gradient-weighted Class Activation Mapping (GRAD- CAM) to visually explain the disruption of model attention under attack and its restoration after defense. All experiments are conducted on the Kaggle T4 GPU platform, and the full pipeline is deployed as an interactive Streamlit web application.

The successful emergence of deep learning (DL) in wireless system applications has raised concerns about new security-related challenges. One such security challenge is adversarial attacks. Although there has been much work demonstrating the susceptibility of DL-based classification tasks to adversarial attacks, regression-based problems in the context of a wireless system have not been studied so far from an attack perspective. The aim of this paper is twofold: (i) we consider a regression problem in a wireless setting and show that adversarial attacks can break the DL-based approach and (ii) we analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly. Specifically, the wireless application considered in this paper is the DL-based power allocation in the downlink of a multicell massive multi-input-multi-output system, where the goal of the attack is to yield an infeasible solution by the DL model. We extend the gradient-based adversarial attacks: fast gradient sign method (FGSM), momentum iterative FGSM, and projected gradient descent method to analyze the susceptibility of the considered wireless application with and without adversarial training. We analyze the deep neural network (DNN) models performance against these attacks, where the adversarial perturbations are crafted using both the white-box and black-box attacks.

ZeroGrad: Costless conscious remedies for catastrophic overfitting in the FGSM adversarial training

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

In this paper, a novel black box adversarial computer vision attack is proposed. The introduced attack is based on removing from images some components described by their Tchebichef discrete orthogonal moments, rather than to perturb them. The contribution of this work is focused on the addition of one more clue, supporting the critical hypothesis that computer vision systems fail because they support their decisions not only in robust features but also in others non-robust ones. In this, context non-robust image features described in terms of Tchebichef moments are excluded from the original images and the approximated reconstructed versions of them are used as adversarial examples in order to attack some popular deep learning models. The experiments justify the effectiveness of the proposed adversarial attack in terms of imperceptibility and recognition error rate of the deep learning classifiers. It is worth noting that the top-1 accuracy of the attacked models was degraded by a factor between 9.48%-70.89% for adversarial images of 65dB to 57dB PSNR values. The corresponding degradation of the top-5 models’ accuracy was between 6.9% and 55.14% for the same quality images. Moreover, the proposed attack seems to have more strength than the Fast Gradient Sign Method (FGSM) attacking method traditionally applying in most cases. These results reveal that the proposed attack is able to exploit the vulnerability of the deep learning models’ towards degrading their generalization abilities. In this paper, a novel black box adversarial computer vision attack is proposed. The introduced attack is based on removing from images some components described by their Tchebichef discrete orthogonal moments, rather than to perturb them. The contribution of this work is focused on the addition of one more clue, supporting the critical hypothesis that computer vision systems fail because they support their decisions not only in robust features but also in others non-robust ones. In this, context non-robust image features described in terms of Tchebichef moments are excluded from the original images and the approximated reconstructed versions of them are used as adversarial examples in order to attack some popular deep learning models. The experiments justify the effectiveness of the proposed adversarial attack in terms of imperceptibility and recognition error rate of the deep learning classifiers. It is worth noting that the top-1 accuracy of the attacked models was degraded by a factor between 9.48%-70.89% for adversarial images of 65dB to 57dB PSNR values. The corresponding degradation of the top-5 models’ accuracy was between 6.9% and 55.14% for the same quality images. Moreover, the proposed attack seems to have more strength than the Fast Gradient Sign Method (FGSM) attacking method traditionally applying in most cases. These results reveal that the proposed attack is able to exploit the vulnerability of the deep learning models’ towards degrading their generalization abilities.

This chapter introduces the concept of adversarial attacks on image classification models built on convolutional neural networks (CNN). CNNs are very popular deep-learning models which are used in image classification tasks. However, very powerful and pre-trained CNN models working very accurately on image datasets for image classification tasks may perform disastrously when the networks are under adversarial attacks. In this work, two very well-known adversarial attacks are discussed and their impact on the performance of image classifiers is analyzed. These two adversarial attacks are the fast gradient sign method (FGSM) and adversarial patch attack. These attacks are launched on three powerful pre-trained image classifier architectures, ResNet-34, GoogleNet, and DenseNet-161. The classification accuracy of the models in the absence and presence of the two attacks are computed on images from the publicly accessible ImageNet dataset. The results are analyzed to evaluate the impact of the attacks on the image classification task.

Although deep neural networks (DNNs) have achieved high performance across various applications, they are often deceived by adversarial examples generated by adding small perturbations. To combat adversarial attacks, many detection methods have been proposed, including feature squeezing and trapdoor. However, these methods rely on the output of DNNs or involve training a separate network to detect adversarial examples, which leads to high computational costs and low efficiency. In this study, we propose a simple and effective approach called the entropy-based detector (EBD) to protect DNNs from various adversarial attacks. EBD detects adversarial examples by comparing the difference in entropy between the input sample before and after bit depth reduction. We show that EBD can detect over 98% of the adversarial examples generated by attacks using fast-gradient sign method, basic iterative method, momentum iterative method, DeepFool and CW attacks when the false positive rate is 2.5% for CIFAR-10 and ImageNet datasets.

Although fast adversarial training has demonstrated both robustness and efficiency, the problem of "catastrophic overfitting" has been observed. This is a phenomenon in which, during single-step adversarial training, the robust accuracy against projected gradient descent (PGD) suddenly decreases to 0% after a few epochs, whereas the robust accuracy against fast gradient sign method (FGSM) increases to 100%. In this paper, we demonstrate that catastrophic overfitting is very closely related to the characteristic of single-step adversarial training which uses only adversarial examples with the maximum perturbation, and not all adversarial examples in the adversarial direction, which leads to decision boundary distortion and a highly curved loss surface. Based on this observation, we propose a simple method that not only prevents catastrophic overfitting, but also overrides the belief that it is difficult to prevent multi-step adversarial attacks with single-step adversarial training.

Adversarial attacks aim to deceive the target system. Recently, deep learning methods have become a target of adversarial attacks. Even small perturbations could lead to classification errors in deep learning models. In an intrusion detection system using deep learning method, adversarial attack can cause classification error and malicious traffic can be classified as benign. In this study, the effects of adversarial attacks on the accuracy of deep learning-based intrusion detection systems were examined. CICIDS2017 dataset was used to test the detection systems . At first, DDoS attacks weredetected using Autoencoder, MLP, AEMLP, DNN, AEDNN, CNN and AECNN methods. Then, the Fast Gradient Sign Method (FGSM) is used to perform adversarial attacks. Finally, the sensitivity of the methods against the adversarial attacks were examined. Our results showed that the classification performance of deep learning based detection methods decreased up to %17 after the adversarial attacks. The results obtained in this study form the basis for the validation and validation studies of learning-based intrusion detection systems.

The adversarial attack is a cutting-edge technique used to study the vulnerability of deep neural networks (DNNs). However, most existing studies focus on the additive perturbation-based attack, which cannot represent real-world corruption and limit their applications. In particular, haze is a common natural phenomenon that significantly corrupts an image, which inevitably poses a potential threat to deep models. In this work, for the first attempt, we study the effects of haze on DNNs from the perspective of adversarial attacks and propose two adversarial haze attack methods. We first propose the optimization-based adversarial haze attack (OAdvHaze) that optimizes the parameters of the atmospheric scattering model with the guidance of a DNN to synthesize a hazy image, which leads to a high attack success rate. To achieve a more efficient attack, we further propose a predictive adversarial haze attack (PAdvHaze) employing a DNN to predict the hazing parameters through a one-step way. To validate the effectiveness of both methods, we conducted extensive experiments on two publicly available datasets, i.e., ILSVRC 2012 and NIPS 2017. OAdvHaze and PAdvHaze achieve comparable attack success rates and transferability to state-of-the-art attacks. This work would contribute to the evaluation and enhancement of the robustness of DNNs against haze perturbation that may happen in the real world.