26 September 2023 in IEEE Communications Surveys & Tutorials
Adversarial attacks and defenses in machine learning and deep neural network (DNN) have been gaining significant attention due to the rapidly growing applications of deep learning in communication networks. This survey provides a comprehensive overview of the recent advancements in the field of adversarial attack and defense techniques, with a focus on DNN-based classification models for communication applications. Specifically, we conduct a comprehensive classification of recent adversarial attack methods and state-of-the-art adversarial defense techniques based on attack principles, and present them in visually appealing tables and tree diagrams. This is based on a rigorous evaluation of the existing works, including an analysis of their strengths and limitations. We also categorize the methods into counter-attack detection and robustness enhancement, with a specific focus on regularizationbased methods for enhancing robustness. New avenues of attack are also explored, including search-based, decision-based, dropbased, and physical-world attacks, and a hierarchical classification of the latest defense methods is provided, highlighting the challenges of balancing training costs with performance, maintaining clean accuracy, overcoming the effect of gradient masking, and ensuring method transferability. At last, the lessons learned and open challenges are summarized with future research opportunities recommended.
30 August 2022 in IEEE Transactions on Information Forensics and Security
Typical deep neural network (DNN) backdoor attacks are based on triggers embedded in inputs. Existing imperceptible triggers are computationally expensive or low in attack success. In this paper, we propose a new backdoor trigger, which is easy to generate, imperceptible, and highly effective. The new trigger is a uniformly randomly generated three-dimensional (3D) binary pattern that can be horizontally and/or vertically repeated and mirrored and superposed onto three-channel images for training a backdoored DNN model. Dispersed throughout an image, the new trigger produces weak perturbation to individual pixels, but collectively holds a strong recognizable pattern to train and activate the backdoor of the DNN. We also analytically reveal that the trigger is increasingly effective with the improving resolution of the images. Experiments are conducted using the ResNet-18 and MLP models on the MNIST, CIFAR-10, and BTSR datasets. In terms of imperceptibility, the new trigger outperforms existing triggers, such as BadNets, Trojaned NN, and Hidden Backdoor, by over an order of magnitude. The new trigger achieves an almost 100% attack success rate, only reduces the classification accuracy by less than 0.7%–2.4%, and invalidates the state-of-the-art defense techniques.
19 May 2023 in IEEE Transactions on Neural Networks and Learning Systems
Deep neural networks (DNNs) are vulnerable to adversarial examples, while adversarial attack models, e.g., DeepFool, are on the rise and outrunning adversarial example detection techniques. This article presents a new adversarial example detector that outperforms state-of-the-art detectors in identifying the latest adversarial attacks on image datasets. Specifically, we propose to use sentiment analysis for adversarial example detection, qualified by the progressively manifesting impact of an adversarial perturbation on the hidden-layer feature maps of a DNN under attack. Accordingly, we design a modularized embedding layer with the minimum learnable parameters to embed the hidden-layer feature maps into word vectors and assemble sentences ready for sentiment analysis. Extensive experiments demonstrate that the new detector consistently surpasses the state-of-the-art detection algorithms in detecting the latest attacks launched against ResNet and Inception neutral networks on the CIFAR-10, CIFAR-100, and SVHN datasets. The detector only has about 2 million parameters and takes less than 4.6 ms to detect an adversarial example generated by the latest attack models using a Tesla K80 GPU card.
7 October 2024 in IEEE Transactions on Information Forensics and Security
Training deep neural networks (DNNs) with altered data, known as adversarial training, is essential for improving their robustness. A significant challenge emerges as the robustness strengthened during training often diminishes during inference, resulting in drops in robust pronounced accuracy. Contemporary strategies either necessitate excessively large training data or risk compromising the natural accuracy of non-adversarial images. Our analysis identifies that the inherent vulnerability of DNNs to adversarial attacks stems from certain input space segments that are inadequately populated by training data, leading to decision-making voids with incorrect predictions. The minimum number of training samples required for successful adversarial training can be attained by maximizing the representativeness of the samples. In light of this, we put forth an advanced training data augmentation method anchored on a Generative Adversarial Network. The generated samples are evaluated by the image classifier during training and selected based on their confidence scores. Evaluations on public datasets, such as Tiny-ImageNet, MS COCO, and CIFAR-100, using various deep neural networks (DNNs), including Vision Transformer, MobileNet, and WideResNet, under recent attacks like DifAttack, SQBA, and AutoAttack, confirm that our method significantly enhances the adversarial robustness of DNN image classifiers. Our method outperforms state-of-the-art adversarial training methods by 35.66% on Tiny-ImageNet, 13.53% on MS COCO, and 13.06% on CIFAR-100.
8 November 2021 in IEEE Transactions on Automation Science and Engineering
Sensory data is only meaningful if correctly associated with originating locations, e.g., in three-dimensional wireless sensor systems inside an aircraft cabin. Received signal strength is a cost-effective option to locate low-cost sensors due to its universal availability, but suffers from coarse ranging accuracy with multiplicative errors. This paper presents a new received signal strength-based approach to locating a large number of low-cost sensors given their possible three-dimensional installation points. Our approach achieves the accuracy which has not been achieved in the literature. The approach first cooperatively locates the sensors in the continuous three-dimensional spaces, then associates the continuous location estimates to the installation points, and finally refines the association with likelihood ascent search. A new convex relaxation-based optimization is designed for cooperative localization in continuous three-dimensional spaces. The Kuhn-Munkres algorithm is generalized for the association. Cramér-Rao Lower Bounds are derived to specify the local three-dimensional regions in which refinement is carried out to improve the final accuracy with little complexity overhead. The proposed approach is validated experimentally with signal strength measurements collected in a Fokker 100 passenger plane, achieves 100% accuracy in all experiments conducted, and outperforms state-of-the-art metaheuristics significantly with much shorter execution time. Note to Practitioners—This paper is motivated by a goal to realize various aircraft automation applications through three-dimensional localization and association of wireless sensors. For example, automatic identification of seat locations can be implemented efficiently with wireless sensors, which enables effortless re-association between control buttons in the seats and the corresponding functions after cabin refurbishment. Meanwhile, automatic detection of missing/misplaced safety equipment can be carried out to improve the efficiency of flight preparation. There currently lacks an received signal strength-based three-dimensional sensor association method in indoor environments. The theoretical framework proposed in this paper aims to utilize the readily available received signal strength measurements to associate Commercial-Off-The-Shelf sensors to their possible installation points. This approach avoids the requirement of labor-intensive fingerprinting effort and high-cost equipment. The proposed approach has been tested and evaluated using both synthetic data and real data collected in a passenger plane as a proof of concept.