About
302
Publications
41,156
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,359
Citations
Publications
Publications (302)
The Transformers architecture has recently emerged as a revolutionary paradigm in the field of deep learning, particularly excelling in Natural Language Processing (NLP) and Computer Vision (CV) applications. Despite its success, the security implications of Transformers have not been comprehensively explored, encompassing a broad spectrum of both...
This paper presents a novel Electrodermal Activity (EDA) signal acquisition system, designed to address the challenges of stress monitoring in contemporary society, where stress affects one in four individuals. Our system focuses on enhancing the accuracy and efficiency of EDA measurements, a reliable indicator of stress. Traditional EDA monitoring...
Automated emotion recognition has applications in various fields, such as human-machine interaction, healthcare, security, education, and emotion-aware recommendation/feedback systems. Developing methods to analyze human emotions accurately is essential to enable such diverse applications. Multiple studies have been conducted to explore the possibi...
Obfuscation stands as a promising solution for safeguarding hardware intellectual property (IP) against a spectrum of threats including reverse engineering, IP piracy, and tampering. In this paper, we introduce Obfus-chat, a novel framework leveraging Generative Pre-trained Transformer (GPT) models to automate the obfuscation process. The proposed...
The Forward-Forward Learning (FFL) algorithm is a recently proposed solution for training neural networks without needing memory-intensive backpropagation. During training, labels accompany input data, classifying them as positive or negative inputs. Each layer learns its response to these inputs independently. In this study, we enhance the FFL wit...
The growing complexity of contemporary computing systems heightens susceptibility to emerging cyber threats. Recent advancements in computer architecture security leverage Hardware Performance Counters (HPCs) registers to monitor applications behavior and access low-level features. The integration of Machine Learning (ML) techniques emerges as a pr...
Malware is increasingly becoming a significant threat to computing systems, and detecting zero-day (unknown) malware is crucial to ensure the security of modern systems. These attacks exploit software security vulnerabilities that are not documented or known in the detection mechanism’s database, making it particularly a pressing challenge to addre...
Transient execution attacks pose information leakage risks in current systems. Disabling speculative execution, though mitigating the issue, results in significant performance loss. Accurate identification of vulnerable gadgets is essential for balancing security and performance. However, uncovering all covert channels is challenging due to complex...
On-chip learning is the process of training or updating machine learning models directly on specialized hardware. This approach differs from traditional machine learning, which typically conducts training on external computing resources like Central Processing Units (CPUs) or Graphics Processing Units (GPUs). On-chip learning offers several advanta...
The deployment of Large Language Models (LLMs) into edge and embedded devices marks a transformative step in integrating Artificial Intelligence (AI) into real-world applications. This integration is crucial as it enables efficient, localized processing, reducing reliance on cloud computing and enhancing data privacy by keeping sensitive informatio...
The globalization of the manufacturing process and the supply chain for electronic hardware has been driven by the need to maximize profitability while lowering risk in a technologically advanced silicon sector. However, many hardware IPs’ security features have been broken because of the rise in successful hardware attacks. Existing security effor...
UNSTRUCTURED
Pain, as a highly individualized experience, stands as a primary reason driving individuals towards seeking medical attention. The assessment of pain traditionally relies upon self-reported or input from caregivers. Yet, the former proves inadequate when dealing with non-communicative patients, while the latter may suffer from subjecti...
Microarchitectural attacks, such as side-channel, exploit shared resources to leak sensitive information. Performing microarchitectural attacks on the cloud is possible once the attacker’s virtual machine (VM) is co-located with the victim’s VM. Hence, the co-location requirement with the victim limits the practicality of microarchitectural attacks...
In recent decades, due to the emerging requirements of computation acceleration, cloud FPGAs have become popular in public clouds. Major cloud service providers, e.g. AWS and Microsoft Azure have provided FPGA computing resources in their infrastructure and have enabled users to design and deploy their own accelerators on these FPGAs. Multi-tenancy...
The Electrocardiogram (ECG) measures the electrical cardiac activity generated by the heart to detect abnormal heartbeat and heart attack. However, the irregular occurrence of the abnormalities demands continuous monitoring of heartbeats. Machine learning techniques are leveraged to automate the task to reduce labor work needed during monitoring. I...
With the growth and globalization of IC design and development, there is an increase in the number of Designers and Design houses. As setting up a fabrication facility may easily cost upwards of $20 billion, costs for advanced nodes may be even greater. IC design houses that cannot produce their chips in-house have no option but to use external fou...
This paper discloses a Reinforcement Learning (RL) solution implemented to decrease the peak current by alteration of the clock skews. Clock skews are elements of the clock network calculated throughout the Clock Tree Synthesis (CTS) phase of physical design. Initially, the physical design tools targeted obtaining a balanced clock tree and decreasi...
Deep neural networks (DNNs) are compute-intensive nonlinear mathematical functions that employ matrix/tensor operators at their core to identify temporal and/or spatial correlations within input data. Common techniques, such as pruning, quantization, and compact model design, have been proposed by researchers and extensively utilized by developers...
In this paper, we have identified and addressed pressing challenges associated with online and cost-effective malware detection based on Hardware Performance Counters (HPCs) information. Existing Hardware-Assisted Malware Detection (HMD) methods guided by standard Machine Learning (ML) algorithms have limited their study on detecting known signatur...
Logic obfuscation is introduced as a pivotal defense against multiple hardware threats on Integrated Circuits (ICs), including reverse engineering (RE) and intellectual property (IP) theft. The effectiveness of logic obfuscation is challenged by the recently introduced Boolean satisfiability (SAT) attack and its variants. A plethora of countermeasu...
Undertreatment or overtreatment of pain will cause severe consequences physiologically and psychologically. Thus, researchers have made great efforts to develop automatic pain assessment approaches based on physiological signals using machine learning techniques. However, state-of-art research mainly focuses on verifying the hypothesis that physiol...
Pain is an unpleasant feeling that can reflect a patient's health situation. Since measuring pain is subjective, time-consuming, and needs continuous monitoring, automated pain intensity detection from facial expression holds great potential for smart healthcare applications. Convolutional Neural Networks (CNNs) are recently being used to identify...
In the past, epidemics such as AIDS, measles, SARS, H1N1 influenza, and tuberculosis caused the death of millions of people around the world. In response, intensive research is evolving to design efficient drugs and vaccines. However, studies warn that new pandemics such as Coronavirus (COVID-19), variants, and even deadly pandemics can emerge in t...
This paper presents RAPTA, a customized Representation-learning Architecture for automation of feature engineering and predicting the result of Path-based Timing-Analysis early in the physical design cycle. RAPTA offers multiple advantages compared to prior work: 1) It has superior accuracy with errors std ranges 3.9ps~16.05ps in 32nm technology. 2...
This paper presents a novel model training solution, denoted as Adaptive-Gravity, for enhancing the robustness of deep neural network classifiers against adversarial examples. We conceptualize the model parameters/features associated with each class as a mass characterized by its centroid location and the spread (standard deviation of the distance)...
In today’s substantial data era, millions of data points are generated in a matter of seconds, making traditional machine learning algorithms difficult to handle. Online learning approaches strive to update the best predictor for the data in a sequential sequence, as a typical strategy used in areas of machine learning to tackle the computational i...
The ever-increasing complexity of modern computing systems has led to the growth of security vulnerabilities, making such systems appealing targets for increasingly sophisticated cyber-attacks. Cybersecurity for the past decades has been at the forefront of global attention as a critical threat to the society, especially the nation’s information te...
Transport, chemical structure, physical connection, social networks, and disease spread are all examples of real-world situations where graphs are used. Applying typical deep learning techniques (such as convolutional neural networks) to this non-Euclidean structure is not straightforward. As a result, graph neural networks (GNNs) are proposed as a...
Logic locking and Integrated Circuit (IC) camouflaging are the most prevalent protection schemes that can thwart most hardware security threats. However, the state-of-the-art attacks, including Boolean Satisfiability (SAT) and approximation-based attacks, question the efficacy of the existing defense schemes. Recent obfuscation schemes have employe...
Resources provisioning on the cloud is problematic due to heterogeneous resources and diverse applications. The complexity of such tasks can be reduced with the aid of Machine Learning. Researchers have found, however, that machine learning poses new threats such as adversarial attacks. Based on our investigation, we found that adversarial ML can t...
Advancements in machine learning led to its adoption into numerous applications ranging from computer vision to security. Despite the achieved advancements in the machine learning, the vulnerabilities in those techniques are as well exploited. Adversarial samples are the samples generated by adding crafted perturbations to the normal input samples....
One of the most powerful scale-out infrastructures to perform massive computation and eliminate the need to maintain high-end expensive computing resources at the user side is Cloud. Cloud architectures are vastly heterogeneous, comprising of large and diverse types of servers. The performance and power consumption of IMC (This has not been defined...
Machine learning is being increasingly utilized in mobile health applications. However, due to considerable variations among sensing platforms, users’ physiological readings, and their behavioral routines, significant performance degradation is observed when the machine learning models are used with new sensor platforms or adopted by new users. A p...
In the prior chapter, we explored supervised learning, its algorithms, and applications. For supervised learning, the user must supply the output labels (target), and the machine learning model is supposed to fit the learning curve to the dataset and labels. However, there are numerous situations in which the data may not be labeled. Algorithms are...
This chapter explores many supervised machine learning algorithms that have gained significant popularity in recent applications. Supervised learning is the process of acquiring knowledge about annotated data and deriving relationships between the input data and the labels. The simplicity and capacity to develop a better model are two of the key ad...
Recommender systems widely exist in a massive number of web applications including news apps, social media platforms, location-based services, and music/video sharing sites. The purpose of recommender systems is to predict user’s actions on items based on the user’s preferences observed from the user’s historical actions. User actions on items can...
Probability theory is a key building component of machine learning. This chapter explores several facets of probability theory through the use of concrete examples. Numerous subjects are explored, including conditional probability, discrete random variables, and continuous random variables. Additionally, the chapter discusses common discrete and co...
This chapter presents SensorNet that is a scalable and low-power embedded deep convolutional neural network (DCNN) designed to classify multimodal time-series signals. Time-series signals generated by different sensor modalities with different sampling rates are first converted into images (2-D signals), and then DCNN is utilized to automatically l...
The previous chapters discussed different supervised and unsupervised learning, in which cases the data is completely labeled or unlabeled. However, there exist other scenarios where the data is labeled partially and critical to learning from the experience of the system. For such scenarios, reinforcement learning can be utilized. Reinforcement lea...
We begin this chapter by explaining the need to understand data to answer different questions about the distribution of data, important features, how to transform features, how to develop models to handle a certain machine learning task, so forth, in different problem domains. Let’s undertake the discussion with Artificial Intelligence (AI) which i...
Logic obfuscation is introduced as a pivotal defense against multiple hardware threats on Integrated Circuits (ICs) including reverse engineering (RE) and intellectual property (IP) theft. The effectiveness of logic obfuscation is challenged by recently introduced Boolean satisfiability (SAT) attack and it’s variants. A plethora of counter measures...
This Special Issue of the IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS) aims to investigate the latest research in the domain of cross-layer design approaches including algorithms, architectures, hardware, and system integration for microintelligent systems processing. In order to avoid computeintensive algorithms ru...
Emerging embedded systems and Internet-of-Things (IoT) devices, which account for a wide range of applications are often highly resource-constrained that are challenging the software-based methods traditionally adopted for detecting and containing cyber-attacks (e.g., malware) in general-purpose computing systems. In addition to the complexity and...
According to recent security analysis reports, malicious software (a.k.a. malware) is rising at an alarming rate in numbers, complexity, and harmful purposes to compromise the security of modern computer systems. Recently, malware detection based on low-level hardware features (e.g., Hardware Performance Counters (HPCs) information) has emerged as...
Cloud computing paradigms have emerged as a major facility to store and process the massive data produced by various business units, public organizations, Internet-of-Things, and cyber-physical systems. To meet users' performance requirements while maximizing resource utilization to achieve cost-efficiency, cloud administrators leverage schedulers...