Defending Against Adversarial Attacks in Deep Learning with Robust Auxiliary Classifiers Utilizing Bit Plane Slicing

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.

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.

CardioDefense: Defending against adversarial attack in ECG classification with adversarial distillation training

Outside the highly publicized victories in the game of Go, there have been numerous successful applications of deep learning in the fields of information retrieval, computer vision, and speech recognition. In cybersecurity, an increasing number of companies have begun exploring the use of deep learning (DL) in a variety of security tasks with malware detection among the more popular. These companies claim that deep neural networks (DNNs) could help turn the tide in the war against malware infection. However, DNNs are vulnerable to adversarial samples, a shortcoming that plagues most, if not all, statistical and machine learning models. Recent research has demonstrated that those with malicious intent can easily circumvent deep learning-powered malware detection by exploiting this weakness. To address this problem, previous work developed defense mechanisms that are based on augmenting training data or enhancing model complexity. However, after analyzing DNN susceptibility to adversarial samples, we discover that the current defense mechanisms are limited and, more importantly, cannot provide theoretical guarantees of robustness against adversarial sampled-based attacks. As such, we propose a new adversary resistant technique that obstructs attackers from constructing impactful adversarial samples by randomly nullifying features within data vectors. Our proposed technique is evaluated on a real world dataset with 14,679 malware variants and 17,399 benign programs. We theoretically validate the robustness of our technique, and empirically show that our technique significantly boosts DNN robustness to adversarial samples while maintaining high accuracy in classification. To demonstrate the general applicability of our proposed method, we also conduct experiments using the MNIST and CIFAR-10 datasets, widely used in image recognition research.

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.

The rapid development of deep neural networks (DNN) has promoted the widespread application of image recognition, natural language processing, and autonomous driving. However, DNN is vulnerable to adversarial examples, such as an input sample with imperceptible perturbation which can easily invalidate the DNN and even deliberately modify the classification results. Therefore, this article proposes a preprocessing defense framework based on image compression reconstruction to achieve adversarial example defense. Firstly, the defense framework performs pixel depth compression on the input image based on the sensitivity of the adversarial example to eliminate adversarial perturbations. Secondly, we use the super-resolution image reconstruction network to restore the image quality and then map the adversarial example to the clean image. Therefore, there is no need to modify the network structure of the classifier model, and it can be easily combined with other defense methods. Finally, we evaluate the algorithm with MNIST, Fashion-MNIST, and CIFAR-10 datasets; the experimental results show that our approach outperforms current techniques in the task of defending against adversarial example attacks.

Deep neural networks have been found to be vulnerable to adversarial attacks. To address this challenge, this paper adopts the evolutionary multi-objective approach to the learning process, and manages to achieve a balance between learning accuracy and robustness against adversarial attacks. In addition, we propose to minimize the model complexity together with the adversarial training loss to defend against fast gradient signed method attacks. Our experimental results using two deep neural networks models, LeNet-5 and VGG-11, on MNIST and CIFAR-10 datasets, respectively, confirm that the proposed methods are effective in improving the robustness of deep learning models against adversarial attacks.

Deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples. Specifically, adding imperceptible perturbations to clean images can fool the well trained deep neural networks. In this paper, we propose an end-to-end image compression model to defend adversarial examples: ComDefend. The proposed model consists of a compression convolutional neural network (ComCNN) and a reconstruction convolutional neural network (ResCNN). The ComCNN is used to maintain the structure information of the original image and purify adversarial perturbations. And the ResCNN is used to reconstruct the original image with high quality. In other words, ComDefend can transform the adversarial image to its clean version, which is then fed to the trained classifier. Our method is a pre-processing module, and does not modify the classifier's structure during the whole process. Therefore it can be combined with other model-specific defense models to jointly improve the classifier's robustness. A series of experiments conducted on MNIST, CIFAR10 and ImageNet show that the proposed method outperforms the state-of-the-art defense methods, and is consistently effective to protect classifiers against adversarial attacks.

In the past years, deep neural networks (DNN) have become popular in many disciplines such as computer vision (CV), natural language processing (NLP), etc. The evolution of hardware has helped researchers to develop many powerful Deep Learning (DL) models to face numerous challenging problems. One of the most important challenges in the CV area is Medical Image Analysis in which DL models process medical images—such as magnetic resonance imaging (MRI), X-ray, computed tomography (CT), etc.—using convolutional neural networks (CNN) for diagnosis or detection of several diseases. The proper function of these models can significantly upgrade the health systems. However, recent studies have shown that CNN models are vulnerable under adversarial attacks with imperceptible perturbations. In this paper, we summarize existing methods for adversarial attacks, detections and defenses on medical imaging. Finally, we show that many attacks, which are undetectable by the human eye, can degrade the performance of the models, significantly. Nevertheless, some effective defense and attack detection methods keep the models safe to an extent. We end with a discussion on the current state-of-the-art and future challenges.

Given their outstanding performance, the Deep Neural Networks (DNNs) models have been deployed in many real-world applications. However, recent studies have demonstrated that they are vulnerable to small carefully crafted perturbations, i.e., adversarial examples, which considerably decrease their performance and can lead to devastating consequences, especially for safety-critical applications, such as autonomous vehicles, healthcare and face recognition. Therefore, it is of paramount importance to offer defense solutions that increase the robustness of DNNs against adversarial attacks. In this paper, we propose a novel defense solution based on a Deep Denoising Sparse Autoencoder (DDSA). The proposed method is performed as a pre-processing step, where the adversarial noise of the input samples is removed before feeding the classifier. The pre-processing defense block can be associated with any classifier, without any change to their architecture or training procedure. In addition, the proposed method is a universal defense, since it does not require any knowledge about the attack, making it usable against any type of attack. The experimental results on MNIST and CIFAR-10 datasets have shown that the proposed DDSA defense provides a high robustness against a set of prominent attacks under white-, gray- and black-box settings, and outperforms state-of-the-art defense methods.

Foster the mechanical design of artificial vision requires a delicate balance between high-level analytical methods and the discovery through metaheuristics of near-optimal functions working towards complex visual problems. Evolutionary computation and swarm intelligence have developed strategies that automatically design meaningful deep convolutional neural network architectures to create better image classifiers. However, these architectures have not surpassed hand-craft models working with outdated problems with datasets of icon images. Nowadays, recent concerns about deep convolutional neural networks to adversarial attacks in the form of modifications to the input image can manipulate their output to make them untrustworthy. Brain programming is a hyper-heuristic whose aim is to work at a higher level of abstraction to develop automatically artificial visual cortex algorithms for a problem domain like image classification. This work's primary goal is to employ brain programming to design an artificial visual cortex to produce accurate and robust image classifiers in two problems. We analyze the final models designed by brain programming with the assumption of fooling the system using two adversarial attacks. In both experiments, brain programming constructed artificial brain models capable of competing with hand-crafted deep convolutional neural networks without any influence in the predictions when an adversarial attack is present.

Recent development in the field of Deep Learning have exposed the underlying vulnerability of Deep Neural Network (DNN) against adversarial examples. In image classification, an adversarial example is a carefully modified image that is visually imperceptible to the original image but can cause DNN model to misclassify it. Training the network with Gaussian noise is an effective technique to perform model regularization, thus improving model robustness against input variation. Inspired by this classical method, we explore to utilize the regularization characteristic of noise injection to improve DNN's robustness against adversarial attack. In this work, we propose Parametric-Noise-Injection (PNI) which involves trainable Gaussian noise injection at each layer on either activation or weights through solving the min-max optimization problem, embedded with adversarial training. These parameters are trained explicitly to achieve improved robustness. To the best of our knowledge, this is the first work that uses trainable noise injection to improve network robustness against adversarial attacks, rather than manually configuring the injected noise level through cross-validation. The extensive results show that our proposed PNI technique effectively improves the robustness against a variety of powerful white-box and black-box attacks such as PGD, C & W, FGSM, transferable attack and ZOO attack. Last but not the least, PNI method improves both clean- and perturbed-data accuracy in comparison to the state-of-the-art defense methods, which outperforms current unbroken PGD defense by 1.1 % and 6.8 % on clean test data and perturbed test data respectively using Resnet-20 architecture.

Deep convolutional neural networks have achieved great success in recent years. They have been widely used in various applications such as optical and SAR image scene classification, object detection and recognition, semantic segmentation, and change detection. However, deep neural networks rely on large-scale high-quality training data, and can only guarantee good performance when the training and test data are independently sampled from the same distribution. Deep convolutional neural networks are found to be vulnerable to subtle adversarial perturbations. This adversarial vulnerability prevents the deployment of deep neural networks in security-sensitive applications such as medical, surveillance, autonomous driving and military scenarios. This paper first presents a holistic view of security issues for deep convolutional neural network-based image recognition systems. The entire information processing chain is analyzed regarding safety and security risks. In particular, poisoning attacks and evasion attacks on deep convolutional neural networks are analyzed in detail. The root causes of adversarial vulnerabilities of deep recognition models are also discussed. Then, we give a formal definition of adversarial robustness and present a comprehensive review of adversarial attacks, adversarial defense, and adversarial robustness evaluation. Rather than listing existing research, we focus on the threat models for the adversarial attack and defense arms race. We perform a detailed analysis of several representative adversarial attacks on SAR image recognition models and provide an example of adversarial robustness evaluation. Finally, several open questions are discussed regarding recent research progress from our workgroup. This paper can be further used as a reference to develop more robust deep neural network-based image recognition models in dynamic adversarial scenarios.

A survey on adversarial attacks in computer vision: Taxonomy, visualization and future directions

Masking and purifying inputs for blocking textual adversarial attacks