اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدTaking Care of The Discretization Problem: A Comprehensive Study of the Discretization Problem and A Black-Box Adversarial Attack in Discrete Integer Domain
54
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Numerous methods for crafting adversarial examples were proposed recently with high success rate. Since most existing machine learning based classifiers normalize images into some continuous, real vector, domain firstly, attacks often craft adversarial examples in such domain. However, adversarial examples may become benign after denormalizing them back into the discrete integer domain, known as the discretization problem. This problem was mentioned in some work, but has received relatively little attention. In this work, we first conduct a comprehensive study of existing methods and tools for crafting. We theoretically analyze 34 representative methods and empirically study 20 representative open source tools for crafting adversarial images. Our study reveals that the discretization problem is far more serious than originally thought. This suggests that the discretization problem should be taken into account seriously when crafting adversarial examples and measuring attack success rate. As a first step towards addressing this problem in black-box scenario, we propose a black-box method which reduces the adversarial example searching problem to a derivative-free optimization problem. Our method is able to craft adversarial images by derivative-free search in the discrete integer domain. Experimental results show that our method is comparable to recent white-box methods (e.g., FGSM, BIM and C&W) and achieves significantly higher success rate in terms of adversarial examples in the discrete integer domain than recent black-box methods (e.g., ZOO, NES-PGD and Bandits). Moreover, our method is able to handle models that is non-differentiable and successfully break the winner of NIPS 2017 competition on defense with 95% success rate. Our results suggest that discrete optimization algorithms open up a promising area of research into effective black-box attacks.
قيم البحث
اقرأ أيضاً
Zeroth-order optimization is an important research topic in machine learning. In recent years, it has become a key tool in black-box adversarial attack to neural network based image classifiers. However, existing zeroth-order optimization algorithms
rarely extract second-order information of the model function. In this paper, we utilize the second-order information of the objective function and propose a novel textit{Hessian-aware zeroth-order algorithm} called texttt{ZO-HessAware}. Our theoretical result shows that texttt{ZO-HessAware} has an improved zeroth-order convergence rate and query complexity under structured Hessian approximation, where we propose a few approximation methods for estimating Hessian. Our empirical studies on the black-box adversarial attack problem validate that our algorithm can achieve improved success rates with a lower query complexity.
Applications of machine learning (ML) models and convolutional neural networks (CNNs) have been rapidly increased. Although ML models provide high accuracy in many applications, recent investigations show that such networks are highly vulnerable to a
dversarial attacks. The black-box adversarial attack is one type of attack that the attacker does not have any knowledge about the model or the training dataset. In this paper, we propose a novel approach to generate a black-box attack in sparse domain whereas the most important information of an image can be observed. Our investigation shows that large sparse components play a critical role in the performance of the image classifiers. Under this presumption, to generate adversarial example, we transfer an image into a sparse domain and put a threshold to choose only k largest components. In contrast to the very recent works that randomly perturb k low frequency (LoF) components, we perturb k largest sparse (LaS)components either randomly (query-based) or in the direction of the most correlated sparse signal from a different class. We show that LaS components contain some middle or higher frequency components information which can help us fool the classifiers with a fewer number of queries. We also demonstrate the effectiveness of this approach by fooling the TensorFlow Lite (TFLite) model of Google Cloud Vision platform. Mean squared error (MSE) and peak signal to noise ratio (PSNR) are used as quality metrics. We present a theoretical proof to connect these metrics to the level of perturbation in the sparse domain. We tested our adversarial examples to the state-of-the-art CNNs and support vector machine (SVM) classifiers on color and grayscale image datasets. The results show the proposed method can highly increase the misclassification rate of the classifiers.
Nowadays, digital facial content manipulation has become ubiquitous and realistic with the success of generative adversarial networks (GANs), making face recognition (FR) systems suffer from unprecedented security concerns. In this paper, we investig
ate and introduce a new type of adversarial attack to evade FR systems by manipulating facial content, called textbf{underline{a}dversarial underline{mor}phing underline{a}ttack} (a.k.a. Amora). In contrast to adversarial noise attack that perturbs pixel intensity values by adding human-imperceptible noise, our proposed adversarial morphing attack works at the semantic level that perturbs pixels spatially in a coherent manner. To tackle the black-box attack problem, we devise a simple yet effective joint dictionary learning pipeline to obtain a proprietary optical flow field for each attack. Our extensive evaluation on two popular FR systems demonstrates the effectiveness of our adversarial morphing attack at various levels of morphing intensity with smiling facial expression manipulations. Both open-set and closed-set experimental results indicate that a novel black-box adversarial attack based on local deformation is possible, and is vastly different from additive noise attacks. The findings of this work potentially pave a new research direction towards a more thorough understanding and investigation of image-based adversarial attacks and defenses.
Adversarial examples are perturbed inputs that are designed (from a deep learning networks (DLN) parameter gradients) to mislead the DLN during test time. Intuitively, constraining the dimensionality of inputs or parameters of a network reduces the s
pace in which adversarial examples exist. Guided by this intuition, we demonstrate that discretization greatly improves the robustness of DLNs against adversarial attacks. Specifically, discretizing the input space (or allowed pixel levels from 256 values or 8-bit to 4 values or 2-bit) extensively improves the adversarial robustness of DLNs for a substantial range of perturbations for minimal loss in test accuracy. Furthermore, we find that Binary Neural Networks (BNNs) and related variants are intrinsically more robust than their full precision counterparts in adversarial scenarios. Combining input discretization with BNNs furthers the robustness even waiving the need for adversarial training for certain magnitude of perturbation values. We evaluate the effect of discretization on MNIST, CIFAR10, CIFAR100 and Imagenet datasets. Across all datasets, we observe maximal adversarial resistance with 2-bit input discretization that incurs an adversarial accuracy loss of just ~1-2% as compared to clean test accuracy.
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can defeat both
vanilla DNNs and those generated by various defense techniques developed recently. Instead of searching for an optimal adversarial example for a benign input to a targeted DNN, our algorithm finds a probability density distribution over a small region centered around the input, such that a sample drawn from this distribution is likely an adversarial example, without the need of accessing the DNNs internal layers or weights. Our approach is universal as it can successfully attack different neural networks by a single algorithm. It is also strong; according to the testing against 2 vanilla DNNs and 13 defended ones, it outperforms state-of-the-art black-box or white-box attack methods for most test cases. Additionally, our results reveal that adversarial training remains one of the best defense techniques, and the adversarial examples are not as transferable across defended DNNs as them across vanilla DNNs.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
