Adversarial attacks pose a significant challenge to the reliable deployment of machine learning models in EdgeAI applications, such as autonomous driving and surveillance, which rely on resource-constrained devices for real-time inference. Among these, patch-based adversarial attacks, where small malicious patches (e.g., stickers) are applied to objects, can deceive neural networks into making incorrect predictions with potentially severe consequences. In this paper, we present PatchBlock, a lightweight framework designed to detect and neutralize adversarial patches in images. Leveraging outlier detection and dimensionality reduction, PatchBlock identifies regions affected by adversarial noise and suppresses their impact. It operates as a pre-processing module at the sensor level, efficiently running on CPUs in parallel with GPU inference, thus preserving system throughput while avoiding additional GPU overhead. The framework follows a three-stage pipeline: splitting the input into chunks (Chunking), detecting anomalous regions via a redesigned isolation forest with targeted cuts for faster convergence (Separating), and applying dimensionality reduction on the identified outliers (Mitigating). PatchBlock is both model- and patch-agnostic, can be retrofitted to existing pipelines, and integrates seamlessly between sensor inputs and downstream models. Evaluations across multiple neural architectures, benchmark datasets, attack types, and diverse edge devices demonstrate that PatchBlock consistently improves robustness, recovering up to 77% of model accuracy under strong patch attacks such as the Google Adversarial Patch, while maintaining high portability and minimal clean accuracy loss. Additionally, PatchBlock outperforms the state-of-the-art defenses in efficiency, in terms of computation time and energy consumption per sample, making it suitable for EdgeAI applications.

Adversarial attacks present a significant challenge to the dependable deployment of machine learning models, with patch-based attacks being particularly potent. These attacks introduce adversarial perturbations in localized regions of an image, deceiving even well-trained models. In this paper, we propose Outlier Detection and Dimension Reduction (ODDR), a comprehensive defense strategy engineered to counteract patch-based adversarial attacks through advanced statistical methodologies. Our approach is based on the observation that input features corresponding to adversarial patches-whether naturalistic or synthetic-deviate from the intrinsic distribution of the remaining image data and can thus be identified as outliers. ODDR operates through a robust three-stage pipeline: Fragmentation, Segregation, and Neutralization. This model-agnostic framework is versatile, offering protection across various tasks, including image classification, object detection, and depth estimation, and is proved effective in both CNN-based and Transformer-based architectures. In the Fragmentation stage, image samples are divided into smaller segments, preparing them for the Segregation stage, where advanced outlier detection techniques isolate anomalous features linked to adversarial perturbations. The Neutralization stage then applies dimension reduction techniques to these outliers, effectively neutralizing the adversarial impact while preserving critical information for the machine learning task. Extensive evaluation on benchmark datasets against state-of-the-art adversarial patches underscores the efficacy of ODDR. Our method enhances model accuracy from 39.26% to 79.1% under the GoogleAp attack, outperforming leading defenses such as LGS (53.86%), Jujutsu (60%), and Jedi (64.34%).

Patch-based adversarial attacks were proven to compromise the robustness and reliability of computer vision systems. However, their conspicuous and easily detectable nature challenge their practicality in real-world setting. To address this, recent work has proposed using Generative Adversarial Networks (GANs) to generate naturalistic patches that may not attract human attention. However, such approaches suffer from a limited latent space making it challenging to produce a patch that is efficient, stealthy, and robust to multiple real-world transformations. This paper introduces a novel approach that produces a Dynamic Adversarial Patch (DAP) designed to overcome these limitations. DAP maintains a naturalistic appearance while optimizing attack efficiency and robustness to real-world transformations. The approach involves redefining the optimization problem and introducing a novel objective function that incorporates a similarity metric to guide the patch's creation. Unlike GAN-based techniques, the DAP directly modifies pixel values within the patch, providing increased flexibility and adaptability to multiple transformations. Furthermore, most clothing-based physical attacks assume static objects and ignore the possible transformations caused by non-rigid deformation due to changes in a person's pose. To address this limitation, a ‘Creases Transformation’ (CT) block is introduced, enhancing the patch's resilience to a variety of real-world distortions. Experimental results demonstrate that the proposed approach outperforms state-of-the-art attacks, achieving a success rate of up to 82.28% in the digital world when targeting the YOLOv7 detector and 65% in the physical world when targeting YOLOv3tiny detector deployed in edge-based smart cameras.

Adversarial patch-based attacks have shown to be a major deterrent towards the reliable use of machine learning models. These attacks involve the strategic modification of localized patches or specific image areas to deceive trained machine learning models. In this paper, we propose DefensiveDR, a practical mechanism using a dimensionality reduction technique to thwart such patch-based attacks. Our method involves projecting the sample images onto a lower-dimensional space while retaining essential information or variability for effective machine learning tasks. We perform this using two techniques, Singular Value Decomposition and t-Distributed Stochastic Neighbor Embedding. We experimentally tune the variability to be preserved for optimal performance as a hyper-parameter. This dimension reduction substantially mitigates adversarial perturbations, thereby enhancing the robustness of the given machine learning model. Our defense is model-agnostic and operates without assumptions about access to model decisions or model architectures, making it effective in both black-box and white-box settings. Furthermore, it maintains accuracy across various models and remains robust against several unseen patch-based attacks. The proposed defensive approach improves the accuracy from 38.8% (without defense) to 66.2% (with defense) when performing LaVAN and GoogleAp attacks, which supersedes that of the prominent state-of-the-art like LGS [19] (53.86%) and Jujutsu [7] (60%).

Adversarial patch attacks pose a significant threat to the practical deployment of deep learning systems. However, existing research primarily focuses on image pre-processing defenses, which often result in reduced classification accuracy for clean images and fail to effectively counter physically feasible attacks. In this paper, we investigate the behavior of adversarial patches as anomalies within the distribution of image information and leverage this insight to develop a robust defense strategy. Our proposed defense mechanism utilizes a clustering-based technique called DBSCAN to isolate anomalous image segments, which is carried out by a three-stage pipeline consisting of Segmenting, Isolating, and Blocking phases to identify and mitigate adversarial noise. Upon identifying adversarial components, we neutralize them by replacing them with the mean pixel value, surpassing alternative replacement options. Our model-agnostic defense mechanism is evaluated across multiple models and datasets, demonstrating its effectiveness in countering various adversarial patch attacks in image classification tasks. Our proposed approach significantly improves accuracy, increasing from $38.8 \%$ without the defense to $67.1 \%$ with the defense against LaVAN and GoogleAp attacks, surpassing prominent state-of-the-art methods such as LGS [1] ($53.86 \%$) and Jujutsu [2] (60%).

Physical adversarial attacks pose a significant practical threat as it deceives deep learning systems operating in the real world by producing prominent and maliciously designed physical perturbations. Emphasizing the evaluation of naturalness is crucial in such attacks, as humans can easily detect unnatural manipulations. To address this, recent work has proposed leveraging generative adversarial networks (GANs) to generate naturalistic patches, which may seem visually suspicious and evade human’s attention. However, these approaches suffer from a limited latent space which leads to an inevitable trade-off between naturalness and attack efficiency. In this paper, we propose a novel approach to generate naturalistic and inconspicuous adversarial patches. Specifically, we redefine the optimization problem by introducing an additional loss term to the total loss. This term works as a semantic constraint to ensure that the generated camouflage pattern holds semantic meaning rather than arbitrary patterns. It leverages similarity metrics-based loss that we optimize within the global adversarial objective function. Our technique is based on directly manipulating the pixel values in the patch, which gives higher flexibility and larger space compared to the GAN-based techniques that are based on indirectly optimizing the patch by modifying the latent vector. Our attack achieves superior success rate of up to $91.19 \%$ and $72 \%$, respectively, in the digital world and when deployed in smart cameras at the edge compared to the GAN-based approach.

Monocular depth estimation (MDE) has advanced significantly, primarily through the integration of convolutional neural networks (CNNs) and more recently, Transformers. However, concerns about their susceptibility to adversarial attacks have emerged, especially in safety-critical domains like autonomous driving and robotic navigation. Existing approaches for assessing CNN-based depth prediction methods have fallen short in inducing comprehensive disruptions to the vision system, often limited to specific local areas. In this paper, we introduce SSAP (Shape-Sensitive Adversarial Patch), a novel approach designed to comprehensively disrupt monocular depth estimation (MDE) in autonomous navigation applications. Our patch is crafted to selectively undermine MDE in two distinct ways: by distorting estimated distances or by creating the illusion of an object disappearing from the system’s perspective. Notably, our patch is shape-sensitive, meaning it considers the specific shape and scale of the target object, thereby extending its influence beyond immediate proximity. Furthermore, our patch is trained to effectively address different scales and distances from the camera. Experimental results demonstrate that our approach induces a mean depth estimation error surpassing 0.5, impacting up to 99% of the targeted region for CNN-based MDE models. Additionally, we investigate the vulnerability of Transformer-based MDE models to patch-based attacks, revealing that SSAP yields a significant error of 0.59 and exerts substantial influence over 99% of the target region on these models.

Machine Learning (ML) architectures have been applied to several applications that involve sensitive data, where a guarantee of users' data privacy is required. Differentially Private Stochastic Gradient Descent (DPSGD) is the state-of-the-art method to train privacy-preserving models. However, DPSGD comes at a considerable accuracy loss leading to sub-optimal privacy/utility trade-offs. Towards investigating new ground for better privacy-utility trade-off, this work questions; (i) if models' hyperparameters have any inherent impact on ML models' privacy-preserving properties, and (ii) if models' hyperparameters have any impact on the privacy/utility trade-off of differentially private models. We propose a comprehensive design space exploration of different hyperparameters such as the choice of activation functions, the learning rate and the use of batch normalization. Interestingly, we found that utility can be improved by using Bounded RELU as activation functions with the same privacy-preserving characteristics. With a drop-in replacement of the activation function, we achieve new state-of-the-art accuracy on MNIST (96.02%), FashionMnist (84.76%), and CIFAR-10 (44.42%) without any modification of the learning procedure fundamentals of DPSGD.

Advances in deep-learning have enabled a wide range of promising applications. However, these systems are vulnerable to adversarial attacks; adversarially crafted pertur-bations to their inputs could cause them to misclassify. Most state-of-the-art adversarial attack generation algorithms focus primarily on controlling the noise magnitude to make it undetectable. The execution time is a secondary consideration for these attacks and the underlying assumption is that there are no time constraints. However, just-in-time adversarial attacks where an attacker opportunistically generates adversarial examples on-the-fly represent an even more critical threat, especially against real-time applications. Therefore, this paper introduces a new problem: how to systematically generate adversarial noise under real-time constraints? Understanding this problem improves our understanding of the threat these attacks pose to real-time systems and provides security evaluation benchmarks for future defenses. Therefore, first, we conduct a run-time analysis of adversarial generation algorithms. Our analysis show that universal attacks produce a general attack offline, with no online overhead. However, their success rate is limited because of their generality. In contrast, online algorithms, which target a specific input, are computationally expensive, making them inappropriate under time constraints. Thus, we propose ROOM, a novel Real-time Online-Offline attack construction Model where an offline component warms up the online algorithm, making it possible to generate highly successful attacks under time constraints. Our results show that ROOM can achieve high attack success rates under real-time constraints with up to 90x faster adversarial attack generation than state-of-the-art methods. For example, ROOM achieves 100% adversarial attack success rate on MNIST with a throughput of up to 1250 frame per second (FPS), more than 60% success rate with 200 FPS on CIFAR-10 and 60% with 16 FPS on ImageNet.

The real-world use cases of Machine Learning (ML) have exploded over the past few years. However, the current computing infrastructure is insufficient to support all real-world applications and scenarios. Apart from high efficiency requirements, modern ML systems are expected to be highly reliable against hardware failures as well as secure against adversarial and IP stealing attacks. Privacy concerns are also becoming a first-order issue. This article summarizes the main challenges in agile development of efficient, reliable and secure ML systems, and then presents an outline of an agile design methodology to generate efficient, reliable and secure ML systems based on user-defined constraints and objectives.

In the past few years, an increasing number of machine-learning and deep learning structures, such as Convolutional Neural Networks (CNNs), have been applied to solving a wide range of real-life problems. However, these architectures are vulnerable to adversarial attacks: inputs crafted carefully to force the system output to a wrong label. Since machine-learning is being deployed in safety-critical and security-sensitive domains, such attacks may have catastrophic security and safety consequences. In this paper, we propose for the first time to use hardware-supported approximate computing to improve the robustness of machine learning classifiers. We show that our approximate computing implementation achieves robustness across a wide range of attack scenarios. Specifically, we show that successful adversarial attacks against the exact classifier have poor transferability to the approximate implementation. The transferability is even poorer for the black-box attack scenarios, where adversarial attacks are generated using a proxy model. Surprisingly, the robustness advantages also apply to white-box attacks where the attacker has unrestricted access to the approximate classifier implementation: in this case, we show that substantially higher levels of adversarial noise are needed to produce adversarial examples. Furthermore, our approximate computing model maintains the same level in terms of classification accuracy, does not require retraining, and reduces resource utilization and energy consumption of the CNN. We conducted extensive experiments on a set of strong adversarial attacks; We empirically show that the proposed implementation increases the robustness of a LeNet-5 and an Alexnet CNNs by up to 99% and 87%, respectively for strong transferability-based attacks along with up to 50% saving in energy consumption due to the simpler nature of the approximate logic. We also show that a white-box attack requires a remarkably higher noise budget to fool the approximate classifier, causing an average of 4 dB degradation of the PSNR of the input image relative to the images that succeed in fooling the exact classifier.

Floating point arithmetic is one of the most commonly used units in nowadays computing systems and is deployed for a wide range of domains and applications. While floating point operators offer high precision calculations, a plethora of applications such as multimedia processing and machine learning tolerate errors and computation imprecision. In a context of limited power budget embedded systems, saving resources and energy with an acceptable precision loss is a challenging design task. Approximate computing is an emerging systems design paradigm that offers promising balance between accuracy on the one hand and power consumption and resource utilization on the other hand. While state of the art approximate techniques offer a wide design space at the operator level, few are the works that consider exploring different techniques to build a heterogeneous comprehensive approximate design. In this paper, we propose HEAP: a heterogeneous approximate floating point multiplier. Based on a design space exploration process, we present an approximation at the transistor level that reduces energy consumption of up to 68%. Experimental study on a set of machine learning applications shows promising results with comparable accuracy to exact multiplier based systems.