2022-04-26 更新
Adversarial examples by perturbing high-level features in intermediate decoder layers
Authors:Vojtěch Čermák, Lukáš Adam
We propose a novel method for creating adversarial examples. Instead of perturbing pixels, we use an encoder-decoder representation of the input image and perturb intermediate layers in the decoder. This changes the high-level features provided by the generative model. Therefore, our perturbation possesses semantic meaning, such as a longer beak or green tints. We formulate this task as an optimization problem by minimizing the Wasserstein distance between the adversarial and initial images under a misclassification constraint. We employ the projected gradient method with a simple inexact projection. Due to the projection, all iterations are feasible, and our method always generates adversarial images. We perform numerical experiments on the MNIST and ImageNet datasets in both targeted and untargeted settings. We demonstrate that our adversarial images are much less vulnerable to steganographic defence techniques than pixel-based attacks. Moreover, we show that our method modifies key features such as edges and that defence techniques based on adversarial training are vulnerable to our attacks.
PDF
论文截图
Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis
Authors:Yuwei Sun, Hideya Ochiai, Jun Sakuma
Model poisoning attacks on federated learning (FL) intrude in the entire system via compromising an edge model, resulting in malfunctioning of machine learning models. Such compromised models are tampered with to perform adversary-desired behaviors. In particular, we considered a semi-targeted situation where the source class is predetermined however the target class is not. The goal is to cause the global classifier to misclassify data of the source class. Though approaches such as label flipping have been adopted to inject poisoned parameters into FL, it has been shown that their performances are usually class-sensitive varying with different target classes applied. Typically, an attack can become less effective when shifting to a different target class. To overcome this challenge, we propose the Attacking Distance-aware Attack (ADA) to enhance a poisoning attack by finding the optimized target class in the feature space. Moreover, we studied a more challenging situation where an adversary had limited prior knowledge about a client’s data. To tackle this problem, ADA deduces pair-wise distances between different classes in the latent feature space from shared model parameters based on the backward error analysis. We performed extensive empirical evaluations on ADA by varying the factor of attacking frequency in three different image classification tasks. As a result, ADA succeeded in increasing the attack performance by 1.8 times in the most challenging case with an attacking frequency of 0.01.
PDF
论文截图
Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency
Authors:Xueping Wang, Shasha Li, Min Liu, Yaonan Wang, Amit K. Roy-Chowdhury
The success of deep neural networks (DNNs) has promoted the widespread applications of person re-identification (ReID). However, ReID systems inherit the vulnerability of DNNs to malicious attacks of visually inconspicuous adversarial perturbations. Detection of adversarial attacks is, therefore, a fundamental requirement for robust ReID systems. In this work, we propose a Multi-Expert Adversarial Attack Detection (MEAAD) approach to achieve this goal by checking context inconsistency, which is suitable for any DNN-based ReID systems. Specifically, three kinds of context inconsistencies caused by adversarial attacks are employed to learn a detector for distinguishing the perturbed examples, i.e., a) the embedding distances between a perturbed query person image and its top-K retrievals are generally larger than those between a benign query image and its top-K retrievals, b) the embedding distances among the top-K retrievals of a perturbed query image are larger than those of a benign query image, c) the top-K retrievals of a benign query image obtained with multiple expert ReID models tend to be consistent, which is not preserved when attacks are present. Extensive experiments on the Market1501 and DukeMTMC-ReID datasets show that, as the first adversarial attack detection approach for ReID, MEAAD effectively detects various adversarial attacks and achieves high ROC-AUC (over 97.5%).
PDF Accepted at IEEE ICCV 2021
论文截图
Frequency Centric Defense Mechanisms against Adversarial Examples
Authors:Sanket B. Shah, Param Raval, Harin Khakhi, Mehul S. Raval
Adversarial example (AE) aims at fooling a Convolution Neural Network by introducing small perturbations in the input image.The proposed work uses the magnitude and phase of the Fourier Spectrum and the entropy of the image to defend against AE. We demonstrate the defense in two ways: by training an adversarial detector and denoising the adversarial effect. Experiments were conducted on the low-resolution CIFAR-10 and high-resolution ImageNet datasets. The adversarial detector has 99% accuracy for FGSM and PGD attacks on the CIFAR-10 dataset. However, the detection accuracy falls to 50% for sophisticated DeepFool and Carlini & Wagner attacks on ImageNet. We overcome the limitation by using autoencoder and show that 70% of AEs are correctly classified after denoising.
PDF AdvM ‘21: Proceedings of the 1st International Workshop on Adversarial Learning for Multimedia, at ACM Multimedia ‘21
论文截图
Increased-confidence adversarial examples for deep learning counter-forensics
Authors:Wenjie Li, Benedetta Tondi, Rongrong Ni, Mauro Barni
Transferability of adversarial examples is a key issue to apply this kind of attacks against multimedia forensics (MMF) techniques based on Deep Learning (DL) in a real-life setting. Adversarial example transferability, in fact, would open the way to the deployment of successful counter forensics attacks also in cases where the attacker does not have a full knowledge of the to-be-attacked system. Some preliminary works have shown that adversarial examples against CNN-based image forensics detectors are in general non-transferrable, at least when the basic versions of the attacks implemented in the most popular libraries are adopted. In this paper, we introduce a general strategy to increase the strength of the attacks and evaluate their transferability when such a strength varies. We experimentally show that, in this way, attack transferability can be largely increased, at the expense of a larger distortion. Our research confirms the security threats posed by the existence of adversarial examples even in multimedia forensics scenarios, thus calling for new defense strategies to improve the security of DL-based MMF techniques.
PDF
论文截图
Unauthorized AI cannot Recognize Me: Reversible Adversarial Example
Authors:Jiayang Liu, Weiming Zhang, Kazuto Fukuchi, Youhei Akimoto, Jun Sakuma
In this study, we propose a new methodology to control how user’s data is recognized and used by AI via exploiting the properties of adversarial examples. For this purpose, we propose reversible adversarial example (RAE), a new type of adversarial example. A remarkable feature of RAE is that the image can be correctly recognized and used by the AI model specified by the user because the authorized AI can recover the original image from the RAE exactly by eliminating adversarial perturbation. On the other hand, other unauthorized AI models cannot recognize it correctly because it functions as an adversarial example. Moreover, RAE can be considered as one type of encryption to computer vision since reversibility guarantees the decryption. To realize RAE, we combine three technologies, adversarial example, reversible data hiding for exact recovery of adversarial perturbation, and encryption for selective control of AIs who can remove adversarial perturbation. Experimental results show that the proposed method can achieve comparable attack ability with the corresponding adversarial attack method and similar visual quality with the original image, including white-box attacks and black-box attacks.
PDF arXiv admin note: text overlap with arXiv:1806.09186
论文截图
Essential Features: Content-Adaptive Pixel Discretization to Improve Model Robustness to Adaptive Adversarial Attacks
Authors:Ryan Feng, Wu-chi Feng, Atul Prakash
Preprocessing defenses such as pixel discretization are appealing to remove adversarial attacks due to their simplicity. However, they have been shown to be ineffective except on simple datasets such as MNIST. We hypothesize that existing discretization approaches failed because using a fixed codebook for the entire dataset limits their ability to balance image representation and codeword separability. We propose a per-image adaptive preprocessing defense called Essential Features, which first applies adaptive blurring to push perturbed pixel values back to their original value and then discretizes the image to an image-adaptive codebook to reduce the color space. Essential Features thus constrains the attack space by forcing the adversary to perturb large regions both locally and color-wise for its effects to survive the preprocessing. Against adaptive attacks, we find that our approach increases the $L2$ and $L\infty$ robustness on higher resolution datasets.
PDF
论文截图
Identification of Attack-Specific Signatures in Adversarial Examples
Authors:Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau, Micah Goldblum, Rama Chellappa
The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same constraints. In this work, we show that different attack algorithms produce adversarial examples which are distinct not only in their effectiveness but also in how they qualitatively affect their victims. We begin by demonstrating that one can determine the attack algorithm that crafted an adversarial example. Then, we leverage recent advances in parameter-space saliency maps to show, both visually and quantitatively, that adversarial attack algorithms differ in which parts of the network and image they target. Our findings suggest that prospective adversarial attacks should be compared not only via their success rates at fooling models but also via deeper downstream effects they have on victims.
PDF
论文截图
Improving the Robustness of Adversarial Attacks Using an Affine-Invariant Gradient Estimator
Authors:Wenzhao Xiang, Hang Su, Chang Liu, Yandong Guo, Shibao Zheng
As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI’s inherent vulnerabilities. Designed and trained from certain statistical distributions of data, AI’s deep neural networks (DNNs) remain vulnerable to deceptive inputs that violate a DNN’s statistical, predictive assumptions. Before being fed into a neural network, however, most existing adversarial examples cannot maintain malicious functionality when applied to an affine transformation. For practical purposes, maintaining that malicious functionality serves as an important measure of the robustness of adversarial attacks. To help DNNs learn to defend themselves more thoroughly against attacks, we propose an affine-invariant adversarial attack, which can consistently produce more robust adversarial examples over affine transformations. For efficiency, we propose to disentangle current affine-transformation strategies from the Euclidean geometry coordinate plane with its geometric translations, rotations and dilations; we reformulate the latter two in polar coordinates. Afterwards, we construct an affine-invariant gradient estimator by convolving the gradient at the original image with derived kernels, which can be integrated with any gradient-based attack methods. Extensive experiments on ImageNet, including some experiments under physical condition, demonstrate that our method can significantly improve the affine invariance of adversarial examples and, as a byproduct, improve the transferability of adversarial examples, compared with alternative state-of-the-art methods.
PDF
论文截图
Adversarial Examples on Segmentation Models Can be Easy to Transfer
Authors:Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip Torr
Deep neural network-based image classification can be misled by adversarial examples with small and quasi-imperceptible perturbations. Furthermore, the adversarial examples created on one classification model can also fool another different model. The transferability of the adversarial examples has recently attracted a growing interest since it makes black-box attacks on classification models feasible. As an extension of classification, semantic segmentation has also received much attention towards its adversarial robustness. However, the transferability of adversarial examples on segmentation models has not been systematically studied. In this work, we intensively study this topic. First, we explore the overfitting phenomenon of adversarial examples on classification and segmentation models. In contrast to the observation made on classification models that the transferability is limited by overfitting to the source model, we find that the adversarial examples on segmentations do not always overfit the source models. Even when no overfitting is presented, the transferability of adversarial examples is limited. We attribute the limitation to the architectural traits of segmentation models, i.e., multi-scale object recognition. Then, we propose a simple and effective method, dubbed dynamic scaling, to overcome the limitation. The high transferability achieved by our method shows that, in contrast to the observations in previous work, adversarial examples on a segmentation model can be easy to transfer to other segmentation models. Our analysis and proposals are supported by extensive experiments.
PDF
论文截图
Adaptive Image Transformations for Transfer-based Adversarial Attack
Authors:Zheng Yuan, Jie Zhang, Shiguang Shan
Adversarial attacks provide a good way to study the robustness of deep learning models. One category of methods in transfer-based black-box attack utilizes several image transformation operations to improve the transferability of adversarial examples, which is effective, but fails to take the specific characteristic of the input image into consideration. In this work, we propose a novel architecture, called Adaptive Image Transformation Learner (AITL), which incorporates different image transformation operations into a unified framework to further improve the transferability of adversarial examples. Unlike the fixed combinational transformations used in existing works, our elaborately designed transformation learner adaptively selects the most effective combination of image transformations specific to the input image. Extensive experiments on ImageNet demonstrate that our method significantly improves the attack success rates on both normally trained models and defense models under various settings.
PDF 33 pages, 7 figures, 10 tables
论文截图
Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features
Authors:Hui Liu, Bo Zhao, Minzhi Ji, Yuefeng Peng, Jiabao Guo, Peng Liu
Deep neural networks (DNNs) are under threat from adversarial example attacks. The adversary can easily change the outputs of DNNs by adding small well-designed perturbations to inputs. Adversarial example detection is a fundamental work for robust DNNs-based service. Adversarial examples show the difference between humans and DNNs in image recognition. From a human-centric perspective, image features could be divided into dominant features that are comprehensible to humans, and recessive features that are incomprehensible to humans, yet are exploited by DNNs. In this paper, we reveal that imperceptible adversarial examples are the product of recessive features misleading neural networks, and an adversarial attack is essentially a kind of method to enrich these recessive features in the image. The imperceptibility of the adversarial examples indicates that the perturbations enrich recessive features, yet hardly affect dominant features. Therefore, adversarial examples are sensitive to filtering off recessive features, while benign examples are immune to such operation. Inspired by this idea, we propose a label-only adversarial detection approach that is referred to as feature-filter. Feature-filter utilizes discrete cosine transform to approximately separate recessive features from dominant features, and gets a mutant image that is filtered off recessive features. By only comparing DNN’s prediction labels on the input and its mutant, feature-filter can real-time detect imperceptible adversarial examples at high accuracy and few false positives.
PDF
论文截图