Ali Shahin Shamsabadi

Ali Shahin Shamsabadi

Auto-generated profile, based on publicly available information

Ali Shahin Shamsabadi

Centre for Intelligent Sensing Mary University of London UK

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 January 2020 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
SOSeyed Ali Osia
Seyed Ali Osia
ASAli Shahin Shamsabadi
Ali Shahin Shamsabadi
SSSina Sajadmanesh
Sina Sajadmanesh
ATAli Taheri
Ali Taheri
KKKleomenis Katevas
Kleomenis Katevas
HHHamed Haddadi
Hamed Haddadi
Internet of Things (IoT) devices and applications are being deployed in our homes and workplaces. These devices often rely on continuous data collection to feed machine learning models. However, this approach introduces several privacy and efficiency challenges, as the service operator can perform unwanted inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models, though they remain a challenge for larger, and more complicated models. In this paper, we present a hybrid approach for breaking down large, complex deep neural networks for cooperative, privacy-preserving analytics. To this end, instead of performing the whole operation on the cloud, we let an IoT device to run the initial layers of the neural network, and then send the output to the cloud to feed the remaining layers and produce the final result. In order to ensure that the user’s device contains no extra information except what is necessary for the main task and preventing any secondary inference on the data, we introduce Siamese fine-tuning. We evaluate the privacy benefits of this approach based on the information exposed to the cloud service. We also assess the local inference cost of different layers on a modern handset. Our evaluations show that by using Siamese fine-tuning and at a small processing cost, we can greatly reduce the level of unnecessary, potentially sensitive information in the personal data, and thus achieving the desired trade-off between utility, privacy and performance.

16 April 2020 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
RSRicardo Sanchez-Matilla
Ricardo Sanchez-Matilla
CLChau Yi Li
Chau Yi Li
ASAli Shahin Shamsabadi
Ali Shahin Shamsabadi
RMRiccardo Mazzon
Riccardo Mazzon
ACAndrea Cavallaro
Andrea Cavallaro
Adversarial perturbations can be added to images to protect their content from unwanted inferences. These perturbations may, however, be ineffective against classifiers that were not seen during the generation of the perturbation, or against defenses based on re-quantization, median filtering or JPEG compression. To address these limitations, we present an adversarial attack that is specifically designed to protect visual content against unseen classifiers and known defenses. We craft perturbations using an iterative process that is based on the Fast Gradient Signed Method and that randomly selects a classifier and a defense, in each iteration. This randomization prevents an undesirable overfitting to a specific classifier or defense. We validate the proposed attack in both targeted and untargeted settings on the private classes of the Places365-Standard dataset. Using ResNet18, ResNet50, AlexNet and DenseNet161 as classifiers, the performance of the proposed attack exceeds that of eleven state-of-the-art attacks.

16 April 2020 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
ASAli Shahin Shamsabadi
Ali Shahin Shamsabadi
AGAdria Gascon
Adria Gascon
HHHamed Haddadi
Hamed Haddadi
ACAndrea Cavallaro
Andrea Cavallaro
Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user data, which could lead to significant privacy concerns when dealing with sensitive personal data. To address this problem, we propose PrivEdge, a technique for privacy-preserving MLaaS that safeguards the privacy of users who provide their data for training, as well as users who use the prediction service. With PrivEdge, each user independently uses their private data to locally train a one-class reconstructive adversarial network that succinctly represents their training data. As sending the model parameters to the service provider in the clear would reveal private information, PrivEdge secret-shares the parameters among two non-colluding MLaaS providers, to then provide cryptographically private prediction services through secure multi-party computation techniques. We quantify the benefits of PrivEdge and compare its performance with state-ofthe-art centralised architectures on three privacy-sensitive imagebased tasks: individual identification, writer identification, and handwritten letter recognition. Experimental results show that PrivEdge has high precision and recall in preserving privacy, as well as in distinguishing between private and non-private images. Moreover, we show the robustness of PrivEdge to image compression and biased training data. The source code is available at https://github.com/smartcameras/PrivEdge.

20 September 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ASAli Shahin Shamsabadi
Ali Shahin Shamsabadi
COChangjae Oh
Changjae Oh
ACAndrea Cavallaro
Andrea Cavallaro
We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and the semantics of the labels. The proposed framework combines a structure loss and a semantic adversarial loss in a multi-task objective function to train a fully convolutional neural network. The structure loss helps generate perturbations whose type and magnitude are defined by a target image processing filter. The semantic adversarial loss considers groups of (semantic) labels to craft perturbations that prevent the filtered image from being classified with a label in the same group. We validate our framework with three different target filters, namely detail enhancement, log transformation and gamma correction filters; and evaluate the adversarially filtered images against three classifiers, ResNet50, ResNet18 and AlexNet, pre-trained on ImageNet. We show that the proposed framework generates filtered images with a high success rate, robustness, and transferability to unseen classifiers. We also discuss objective and subjective evaluations of the adversarial perturbations.

12 April 2020 in arXiv
Verified
Preprint
Open access
PDF file
ASAli Shahin Shamsabadi
Ali Shahin Shamsabadi
RSRicardo Sanchez-Matilla
Ricardo Sanchez-Matilla
ACAndrea Cavallaro
Andrea Cavallaro
Adversarial attacks that generate small L_p-norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoising filters and to adversarial training procedures. Instead, adversarial attacks that generate unrestricted perturbations are more robust to defenses, are generally more successful in black-box settings and are more transferable to unseen classifiers. However, unrestricted perturbations may be noticeable to humans. In this paper, we propose a content-based black-box adversarial attack that generates unrestricted perturbations by exploiting image semantics to selectively modify colors within chosen ranges that are perceived as natural by humans. We show that the proposed approach, ColorFool, outperforms in terms of success rate, robustness to defense frameworks and transferability, five state-of-the-art adversarial attacks on two different tasks, scene and object classification, when attacking three state-of-the-art deep neural networks using three standard datasets. The source code is available at https://github.com/smartcameras/ColorFool.

1 June 2022 in arXiv
Verified
Preprint
Open access
PDF file
CLChau Yi Li
Chau Yi Li
RSRicardo Sánchez-Matilla
Ricardo Sánchez-Matilla
ASAli Shahin Shamsabadi
Ali Shahin Shamsabadi
RMRiccardo Mazzon
Riccardo Mazzon
ACAndrea Cavallaro
Andrea Cavallaro
Adversarial attacks modify images with perturbations that change the prediction of classifiers. These modified images, known as adversarial examples, expose the vulnerabilities of deep neural network classifiers. In this paper, we investigate the predictability of the mapping between the classes predicted for original images and for their corresponding adversarial examples. This predictability relates to the possibility of retrieving the original predictions and hence reversing the induced misclassification. We refer to this property as the reversibility of an adversarial attack, and quantify reversibility as the accuracy in retrieving the original class or the true class of an adversarial example. We present an approach that reverses the effect of an adversarial attack on a classifier using a prior set of classification results. We analyse the reversibility of state-of-the-art adversarial attacks on benchmark classifiers and discuss the factors that affect the reversibility.