Universal Perturbation-based Secret Key-Controlled Data Hiding

Deep neural networks (DNNs) are demonstrated to be vulnerable to universal perturbation, a single quasi-perceptible perturbation that can deceive the DNN on most images. However, the previous works are focused on using universal perturbation to perform adversarial attacks, while the potential usability of universal perturbation as data carriers in data hiding is less explored, especially for the key-controlled data hiding method. In this paper, we propose a novel universal perturbation-based secret key-controlled data-hiding method, realizing data hiding with a single universal perturbation and data decoding with the secret key-controlled decoder. Specifically, we optimize a single universal perturbation, which serves as a data carrier that can hide multiple secret images and be added to most cover images. Then, we devise a secret key-controlled decoder to extract different secret images from the single container image constructed by the universal perturbation by using different secret keys. Moreover, a suppress loss function is proposed to prevent the secret image from leakage. Furthermore, we adopt a robust module to boost the decoder's capability against corruption. Finally, A co-joint optimization strategy is proposed to find the optimal universal perturbation and decoder. Extensive experiments are conducted on different datasets to demonstrate the effectiveness of the proposed method. Additionally, the physical test performed on platforms (e.g., WeChat and Twitter) verifies the usability of the proposed method in practice.

Adversarial Examples in the Physical World: A Survey

Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial examples. Besides the attacks in the digital world, the practical implications of adversarial examples in the physical world present significant challenges and safety concerns. However, current research on physical adversarial examples (PAEs) lacks a comprehensive understanding of their unique characteristics, leading to limited significance and understanding. In this paper, we address this gap by thoroughly examining the characteristics of PAEs within a practical workflow encompassing training, manufacturing, and re-sampling processes. By analyzing the links between physical adversarial attacks, we identify manufacturing and re-sampling as the primary sources of distinct attributes and particularities in PAEs. Leveraging this knowledge, we develop a comprehensive analysis and classification framework for PAEs based on their specific characteristics, covering over 100 studies on physical-world adversarial examples. Furthermore, we investigate defense strategies against PAEs and identify open challenges and opportunities for future research. We aim to provide a fresh, thorough, and systematic understanding of PAEs, thereby promoting the development of robust adversarial learning and its application in open-world scenarios.

Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations

Deep neural networks have proven to be vulnerable to adversarial attacks in the form of adding specific perturbations on images to make wrong outputs. Designing stronger adversarial attack methods can help more reliably evaluate the robustness of DNN models. To release the harbor burden and improve the attack performance, auto machine learning (AutoML) has recently emerged as one successful technique to help automatically find the near-optimal adversarial attack strategy. However, existing works about AutoML for adversarial attacks only focus on $L_{\infty}$-norm-based perturbations. In fact, semantic perturbations attract increasing attention due to their naturalnesses and physical realizability. To bridge the gap between AutoML and semantic adversarial attacks, we propose a novel method called multi-objective evolutionary search of variable-length composite semantic perturbations (MES-VCSP). Specifically, we construct the mathematical model of variable-length composite semantic perturbations, which provides five gradient-based semantic attack methods. The same type of perturbation in an attack sequence is allowed to be performed multiple times. Besides, we introduce the multi-objective evolutionary search consisting of NSGA-II and neighborhood search to find near-optimal variable-length attack sequences. Experimental results on CIFAR10 and ImageNet datasets show that compared with existing methods, MES-VCSP can obtain adversarial examples with a higher attack success rate, more naturalness, and less time cost.

RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World

Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches or camouflage to alter the appearance of the target object. However, these approaches generate conspicuous adversarial patterns that show poor stealthiness. Another physical deployable attack is the optical attack, featuring stealthiness while exhibiting weakly in the daytime with sunlight. In this paper, we propose a novel Reflected Light Attack (RFLA), featuring effective and stealthy in both the digital and physical world, which is implemented by placing the color transparent plastic sheet and a paper cut of a specific shape in front of the mirror to create different colored geometries on the target object. To achieve these goals, we devise a general framework based on the circle to model the reflected light on the target object. Specifically, we optimize a circle (composed of a coordinate and radius) to carry various geometrical shapes determined by the optimized angle. The fill color of the geometry shape and its corresponding transparency are also optimized. We extensively evaluate the effectiveness of RFLA on different datasets and models. Experiment results suggest that the proposed method achieves over 99% success rate on different datasets and models in the digital world. Additionally, we verify the effectiveness of the proposed method in different physical environments by using sunlight or a flashlight.

Efficient Search of Comprehensively Robust Neural Architectures via Multi-fidelity Evaluation

Neural architecture search (NAS) has emerged as one successful technique to find robust deep neural network (DNN) architectures. However, most existing robustness evaluations in NAS only consider $l_{\infty}$ norm-based adversarial noises. In order to improve the robustness of DNN models against multiple types of noises, it is necessary to consider a comprehensive evaluation in NAS for robust architectures. But with the increasing number of types of robustness evaluations, it also becomes more time-consuming to find comprehensively robust architectures. To alleviate this problem, we propose a novel efficient search of comprehensively robust neural architectures via multi-fidelity evaluation (ES-CRNA-ME). Specifically, we first search for comprehensively robust architectures under multiple types of evaluations using the weight-sharing-based NAS method, including different $l_{p}$ norm attacks, semantic adversarial attacks, and composite adversarial attacks. In addition, we reduce the number of robustness evaluations by the correlation analysis, which can incorporate similar evaluations and decrease the evaluation cost. Finally, we propose a multi-fidelity online surrogate during optimization to further decrease the search cost. On the basis of the surrogate constructed by low-fidelity data, the online high-fidelity data is utilized to finetune the surrogate. Experiments on CIFAR10 and CIFAR100 datasets show the effectiveness of our proposed method.

A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications

Wide deployment of deep neural networks (DNNs) based applications (e.g., style transfer, cartoonish), stimulating the requirement of copyright protection of such application's production. Although some traditional visible copyright techniques are available, they would introduce undesired traces and result in a poor user experience. In this paper, we propose a novel plug-and-play invisible copyright protection method based on defensive perturbation for DNN-based applications (i.e., style transfer). Rather than apply the perturbation to attack the DNNs model, we explore the potential utilization of perturbation in copyright protection. Specifically, we project the copyright information to the defensive perturbation with the designed copyright encoder, which is added to the image to be protected. Then, we extract the copyright information from the encoded copyrighted image with the devised copyright decoder. Furthermore, we use a robustness module to strengthen the decoding capability of the decoder toward images with various distortions (e.g., JPEG compression), which may be occurred when the user posts the image on social media. To ensure the image quality of encoded images and decoded copyright images, a loss function was elaborately devised. Objective and subjective experiment results demonstrate the effectiveness of the proposed method. We have also conducted physical world tests on social media (i.e., Wechat and Twitter) by posting encoded copyright images. The results show that the copyright information in the encoded image saved from social media can still be correctly extracted.

A Survey on Physical Adversarial Attack in Computer Vision

In the past decade, deep learning has dramatically changed the traditional hand-craft feature manner with strong feature learning capability, resulting in tremendous improvement of conventional tasks. However, deep neural networks have recently been demonstrated vulnerable to adversarial examples, a kind of malicious samples crafted by small elaborately designed noise, which mislead the DNNs to make the wrong decisions while remaining imperceptible to humans. Adversarial examples can be divided into digital adversarial attacks and physical adversarial attacks. The digital adversarial attack is mostly performed in lab environments, focusing on improving the performance of adversarial attack algorithms. In contrast, the physical adversarial attack focus on attacking the physical world deployed DNN systems, which is a more challenging task due to the complex physical environment (i.e., brightness, occlusion, and so on). Although the discrepancy between digital adversarial and physical adversarial examples is small, the physical adversarial examples have a specific design to overcome the effect of the complex physical environment. In this paper, we review the development of physical adversarial attacks in DNN-based computer vision tasks, including image recognition tasks, object detection tasks, and semantic segmentation. For the sake of completeness of the algorithm evolution, we will briefly introduce the works that do not involve the physical adversarial attack. We first present a categorization scheme to summarize the current physical adversarial attacks. Then discuss the advantages and disadvantages of the existing physical adversarial attacks and focus on the technique used to maintain the adversarial when applied into physical environment. Finally, we point out the issues of the current physical adversarial attacks to be solved and provide promising research directions.

A Multi-objective Memetic Algorithm for Auto Adversarial Attack Optimization Design

The phenomenon of adversarial examples has been revealed in variant scenarios. Recent studies show that well-designed adversarial defense strategies can improve the robustness of deep learning models against adversarial examples. However, with the rapid development of defense technologies, it also tends to be more difficult to evaluate the robustness of the defensed model due to the weak performance of existing manually designed adversarial attacks. To address the challenge, given the defensed model, the efficient adversarial attack with less computational burden and lower robust accuracy is needed to be further exploited. Therefore, we propose a multi-objective memetic algorithm for auto adversarial attack optimization design, which realizes the automatical search for the near-optimal adversarial attack towards defensed models. Firstly, the more general mathematical model of auto adversarial attack optimization design is constructed, where the search space includes not only the attacker operations, magnitude, iteration number, and loss functions but also the connection ways of multiple adversarial attacks. In addition, we develop a multi-objective memetic algorithm combining NSGA-II and local search to solve the optimization problem. Finally, to decrease the evaluation cost during the search, we propose a representative data selection strategy based on the sorting of cross entropy loss values of each images output by models. Experiments on CIFAR10, CIFAR100, and ImageNet datasets show the effectiveness of our proposed method.

Searching for Robust Neural Architectures via Comprehensive and Reliable Evaluation

Neural architecture search (NAS) could help search for robust network architectures, where defining robustness evaluation metrics is the important procedure. However, current robustness evaluations in NAS are not sufficiently comprehensive and reliable. In particular, the common practice only considers adversarial noise and quantified metrics such as the Jacobian matrix, whereas, some studies indicated that the models are also vulnerable to other types of noises such as natural noise. In addition, existing methods taking adversarial noise as the evaluation just use the robust accuracy of the FGSM or PGD, but these adversarial attacks could not provide the adequately reliable evaluation, leading to the vulnerability of the models under stronger attacks. To alleviate the above problems, we propose a novel framework, called Auto Adversarial Attack and Defense (AAAD), where we employ neural architecture search methods, and four types of robustness evaluations are considered, including adversarial noise, natural noise, system noise and quantified metrics, thereby assisting in finding more robust architectures. Also, among the adversarial noise, we use the composite adversarial attack obtained by random search as the new metric to evaluate the robustness of the model architectures. The empirical results on the CIFAR10 dataset show that the searched efficient attack could help find more robust architectures.

Deep Monte Carlo Quantile Regression for Quantifying Aleatoric Uncertainty in Physics-informed Temperature Field Reconstruction

For the temperature field reconstruction (TFR), a complex image-to-image regression problem, the convolutional neural network (CNN) is a powerful surrogate model due to the convolutional layer's good image feature extraction ability. However, a lot of labeled data is needed to train CNN, and the common CNN can not quantify the aleatoric uncertainty caused by data noise. In actual engineering, the noiseless and labeled training data is hardly obtained for the TFR. To solve these two problems, this paper proposes a deep Monte Carlo quantile regression (Deep MC-QR) method for reconstructing the temperature field and quantifying aleatoric uncertainty caused by data noise. On the one hand, the Deep MC-QR method uses physical knowledge to guide the training of CNN. Thereby, the Deep MC-QR method can reconstruct an accurate TFR surrogate model without any labeled training data. On the other hand, the Deep MC-QR method constructs a quantile level image for each input in each training epoch. Then, the trained CNN model can quantify aleatoric uncertainty by quantile level image sampling during the prediction stage. Finally, the effectiveness of the proposed Deep MC-QR method is validated by many experiments, and the influence of data noise on TFR is analyzed.