arXiv subjects

Hassan Ali

Publications and source records attributed to Hassan Ali.

29 records · Page 2Linked to original sources

arXiv2022

Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses

Metaverse is expected to emerge as a new paradigm for the next-generation Internet, providing fully immersive and personalised experiences to socialize, work, and play in self-sustaining and hyper-spatio-temporal virtual world(s). The advancements in different technologies like augmented reality, virtual reality, extended reality (XR), artificial intelligence (AI), and 5G/6G communication will be the key enablers behind the realization of AI-XR metaverse applications. While AI itself has many potential applications in the aforementioned technologies (e.g., avatar generation, network optimization, etc.), ensuring the security of AI in critical applications like AI-XR metaverse applications is profoundly crucial to avoid undesirable actions that could undermine users' privacy and safety, consequently putting their lives in danger. To this end, we attempt to analyze the security, privacy, and trustworthiness aspects associated with the use of various AI techniques in AI-XR metaverse applications. Specifically, we discuss numerous such challenges and present a taxonomy of potential solutions that could be leveraged to develop secure, private, robust, and trustworthy AI-XR applications. To highlight the real implications of AI-associated adversarial threats, we designed a metaverse-specific case study and analyzed it through the adversarial lens. Finally, we elaborate upon various open issues that require further research interest from the community.

cs.AI↗

arXiv2022

Visual Heart Rate Estimation from RGB Facial Video using Spectral Reflectance

Estimation of the Heart rate from the facial video has a number of applications in the medical and fitness industries. Additionally, it has become useful in the field of gaming as well. Several approaches have been proposed to seamlessly obtain the Heart rate from the facial video, but these approaches have had issues in dealing with motion and illumination artifacts. In this work, we propose a reliable HR estimation framework using the spectral reflectance of the user, which makes it robust to motion and illumination disturbances. We employ deep learning-based frameworks such as Faster RCNNs to perform face detection as opposed to the Viola Jones algorithm employed by previous approaches. We evaluate our method on the MAHNOB HCI dataset and found that the proposed method is able to outperform previous approaches.Estimation of the Heart rate from facial video has a number of applications in the medical and the fitness industries. Additionally, it has become useful in the field of gaming as well. Several approaches have been proposed to seamlessly obtain the Heart rate from the facial video, but these approaches have had issues in dealing with motion and illumination artifacts. In this work, we propose a reliable HR estimation framework using the spectral reflectance of the user, which makes it robust to motion and illumination disturbances. We employ deep learning-based frameworks such as Faster RCNNs to perform face detection as opposed to the Viola-Jones algorithm employed by previous approaches. We evaluate our method on the MAHNOB HCI dataset and found that the proposed method is able to outperform previous approaches.

cs.CV↗

arXiv2020

HaS-Nets: A Heal and Select Mechanism to Defend DNNs Against Backdoor Attacks for Data Collection Scenarios

We have witnessed the continuing arms race between backdoor attacks and the corresponding defense strategies on Deep Neural Networks (DNNs). Most state-of-the-art defenses rely on the statistical sanitization of the "inputs" or "latent DNN representations" to capture trojan behaviour. In this paper, we first challenge the robustness of such recently reported defenses by introducing a novel variant of targeted backdoor attack, called "low-confidence backdoor attack". We also propose a novel defense technique, called "HaS-Nets". "Low-confidence backdoor attack" exploits the confidence labels assigned to poisoned training samples by giving low values to hide their presence from the defender, both during training and inference. We evaluate the attack against four state-of-the-art defense methods, viz., STRIP, Gradient-Shaping, Februus and ULP-defense, and achieve Attack Success Rate (ASR) of 99%, 63.73%, 91.2% and 80%, respectively. We next present "HaS-Nets" to resist backdoor insertion in the network during training, using a reasonably small healing dataset, approximately 2% to 15% of full training data, to heal the network at each iteration. We evaluate it for different datasets - Fashion-MNIST, CIFAR-10, Consumer Complaint and Urban Sound - and network architectures - MLPs, 2D-CNNs, 1D-CNNs. Our experiments show that "HaS-Nets" can decrease ASRs from over 90% to less than 15%, independent of the dataset, attack configuration and network architecture.

cs.LG↗

arXiv2020

SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters

In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image. We validate our technique on Convolutional DNNs against the state-of-the-art attacks from the open-source Cleverhans library using the MNIST, the CIFAR-10, and the CIFAR-100 datasets. Our experimental results show that the attack success rate, as well as the imperceptibility of the adversarial images, can be significantly reduced by adding effective pre-processing functions, i.e., Sobel filtering.

cs.LG↗

arXiv2020

QuSecNets: Quantization-based Defense Mechanism for Securing Deep Neural Network against Adversarial Attacks

Adversarial examples have emerged as a significant threat to machine learning algorithms, especially to the convolutional neural networks (CNNs). In this paper, we propose two quantization-based defense mechanisms, Constant Quantization (CQ) and Trainable Quantization (TQ), to increase the robustness of CNNs against adversarial examples. CQ quantizes input pixel intensities based on a "fixed" number of quantization levels, while in TQ, the quantization levels are "iteratively learned during the training phase", thereby providing a stronger defense mechanism. We apply the proposed techniques on undefended CNNs against different state-of-the-art adversarial attacks from the open-source \textit{Cleverhans} library. The experimental results demonstrate 50%-96% and 10%-50% increase in the classification accuracy of the perturbed images generated from the MNIST and the CIFAR-10 datasets, respectively, on commonly used CNN (Conv2D(64, 8x8) - Conv2D(128, 6x6) - Conv2D(128, 5x5) - Dense(10) - Softmax()) available in \textit{Cleverhans} library.

cs.LG↗

arXiv2019

Large g factor in bilayer WS$_2$ flakes

The valley of transition metal dichalcogenides provides an additional platform to manipulate spin due to its unique selection rule. Normally, intralayer optical transitions in magnetic field show a Zeeman splitting with g factor of about $-4$. Here we report remarkable valley Zeeman effect exhibited by splitting of excitonic emission in a bilayer WS$_{2}$, with a value of g factor as large as $-16.5$. The observed large g factor results from the interlayer recombination, as the conduction band and valence band are modified in opposite directions by magnetic field in different layers. The interlayer recombination is due to the defect induced inversion symmetry breaking, which is theoretically not accessible in ideal bilayer WS$_{2}$ with inversion symmetry. Large g factor of interlayer emission offers potential benefits for future optical spin control and detection.

cond-mat.mes-hall↗

arXiv2019

RED-Attack: Resource Efficient Decision based Attack for Machine Learning

Due to data dependency and model leakage properties, Deep Neural Networks (DNNs) exhibit several security vulnerabilities. Several security attacks exploited them but most of them require the output probability vector. These attacks can be mitigated by concealing the output probability vector. To address this limitation, decision-based attacks have been proposed which can estimate the model but they require several thousand queries to generate a single untargeted attack image. However, in real-time attacks, resources and attack time are very crucial parameters. Therefore, in resource-constrained systems, e.g., autonomous vehicles where an untargeted attack can have a catastrophic effect, these attacks may not work efficiently. To address this limitation, we propose a resource efficient decision-based methodology which generates the imperceptible attack, i.e., the RED-Attack, for a given black-box model. The proposed methodology follows two main steps to generate the imperceptible attack, i.e., classification boundary estimation and adversarial noise optimization. Firstly, we propose a half-interval search-based algorithm for estimating a sample on the classification boundary using a target image and a randomly selected image from another class. Secondly, we propose an optimization algorithm which first, introduces a small perturbation in some randomly selected pixels of the estimated sample. Then to ensure imperceptibility, it optimizes the distance between the perturbed and target samples. For illustration, we evaluate it for CFAR-10 and German Traffic Sign Recognition (GTSR) using state-of-the-art networks.

cs.CR↗

arXiv2018

High-Responsivity Photodetection by Self-Catalyzed Phase-Pure P-GaAs Nanowire

Defects are detrimental for optoelectronics devices, such as stacking faults can form carrier-transportation barriers, and foreign impurities (Au) with deep-energy levels can form carrier traps and non-radiative recombination centers. Here, we first developed self-catalyzed p-type GaAs nanowires (NWs) with pure zinc blende (ZB) structure, and then fabricated photodetector made by these NWs. Due to absence of stacking faults and suppression of large amount of defects with deep energy levels, the photodetector exhibits room-temperature high photo responsivity of 1.45 x 105 A W^-1 and excellent specific detectivity (D*) up to 1.48 x 10^14 Jones for low-intensity light signal of wavelength 632.8 nm, which outperforms previously reported NW-based photodetectors. These results demonstrate that these self-catalyzed pure-ZB GaAs NWs to be promising candidates for optoelectronics applications.

cond-mat.mes-hall↗

arXiv2017

High-Q microcavity enhanced optical properties of CuInS$_{2}$/ZnS colloidal quantum dots towards non-photodegradation

We report on a temporal evolution of photoluminescence (PL) spectroscopy of CuInS$_{2}$/ZnS colloidal quantum dots (QDs) by drop-casting on SiO$_{2}$/Si substrates and high quality factor microdisks (MDs) under different atmospheric conditions. Fast PL decay, peak blueshift and linewidth broadening due to photooxidation have been observed at low excitation power. With further increasing of the excitation power, the PL peak position shows a redshift and linewidth becomes narrow, which is ascribed to the enhanced F$\ddot{o}$rster resonant energy transfer between different QDs by photoinduced agglomeration. The oxygen plays an important role in optically induced PL decay which is verified by reduced photobleaching effect in vacuum. When the QDs drop-casted on MDs, photooxidation and photobleaching are accelerated because the excitation efficiency is greatly enhanced with coupling the pumping laser with the cavity modes. However, when the emitted photons couple with cavity modes, a PL enhancement by more than 20 times is achieved because of the increased extraction efficiency and Purcell effects of MDs at room temperature (RT), and 35 times at 20 K. The photobleaching can be avoided with a small excitation power but with a strong PL intensity by taking advantages of high quality factor cavities. The high efficient PL emission without photodegradation is very promising for using CuInS$_{2}$ QDs as high efficient photon emitters at RT, where the photodegradation has always been limiting the practical applications of colloidal quantum dots.

physics.optics↗

arXiv2016

Recombination processes in CuInS$_{2}$/ZnS Nanocrystals during steady-state photoluminescence

We report on temperature- and excitation-power-dependent photoluminescence (PL) study of CuInS$_{2}$/ZnS nanocrystals dispersed on a SiO$_{2}$/Si substrate with a confocal micro-PL system. With increasing the excitation power at 22 K and room temperature, the PL spectra are blue-shifted because of the state filling. At low temperature, a small peak is observed at the low energy side of the spectrum, which could be due to the F$\ddot{o}$rster resonance energy transfer between different nanocrystals. The integrated PL intensity increases sublinearly as a function of excitation power with a power factor of around 2/3, which demonstrates the Auger recombination dominated process in the nanocrystals, especially under the high excitation power.

cond-mat.mtrl-sci↗

arXiv2015

Observation of coupling between zero- and two-dimensional semiconductor systems based on anomalous diamagnetic effects

We report the direct observation of coupling between a single self-assembled InAs quantum dot and a wetting layer, based on strong diamagnetic shifts of many-body exciton states using magneto-photoluminescence spectroscopy. An extremely large positive diamagnetic coefficient is observed when an electron in the wetting layer combines with a hole in the quantum dot; the coefficient is nearly one order of magnitude larger than that of the exciton states confined in the quantum dots. Recombination of electrons with holes in a quantum dot of the coupled system leads to an unusual negative diamagnetic effect, which is five times stronger than that in a pure quantum dot system. This effect can be attributed to the expansion of the wavefunction of remaining electrons in the wetting layer or the spread of electrons in the excited states of the quantum dot to the wetting layer after recombination. In this case, the wavefunction extent of the final states in the quantum dot plane is much larger than that of the initial states because of the absence of holes in the quantum dot to attract electrons. The properties of emitted photons that depend on the large electron wavefunction extents in the wetting layer indicate that the coupling occurs between systems of different dimensionality, which is also verified from the results obtained by applying a magnetic field in different configurations. This study paves a new way to observe hybrid states with zero- and two-dimensional structures, which could be useful for investigating the Kondo physics and implementing spin-based solid-state quantum information processing.

cond-mat.mes-hall↗