arXiv subjects

Faruk Kazi

Publications and source records attributed to Faruk Kazi.

5 recordsLinked to original sources

arXiv2024

Converging Dimensions: Information Extraction and Summarization through Multisource, Multimodal, and Multilingual Fusion

Recent advances in large language models (LLMs) have led to new summarization strategies, offering an extensive toolkit for extracting important information. However, these approaches are frequently limited by their reliance on isolated sources of data. The amount of information that can be gathered is limited and covers a smaller range of themes, which introduces the possibility of falsified content and limited support for multilingual and multimodal data. The paper proposes a novel approach to summarization that tackles such challenges by utilizing the strength of multiple sources to deliver a more exhaustive and informative understanding of intricate topics. The research progresses beyond conventional, unimodal sources such as text documents and integrates a more diverse range of data, including YouTube playlists, pre-prints, and Wikipedia pages. The aforementioned varied sources are then converted into a unified textual representation, enabling a more holistic analysis. This multifaceted approach to summary generation empowers us to extract pertinent information from a wider array of sources. The primary tenet of this approach is to maximize information gain while minimizing information overlap and maintaining a high level of informativeness, which encourages the generation of highly coherent summaries.

cs.AI↗

arXiv2023

BLE Protocol in IoT Devices and Smart Wearable Devices: Security and Privacy Threats

Bluetooth Low Energy (BLE) has become the primary transmission media due to its extremely low energy consumption, good network scope, and data transfer speed for the Internet of Things (IoT) and smart wearable devices. With the exponential boom of the Internet of Things (IoT) and the Bluetooth Low Energy (BLE) connection protocol, a requirement to discover defensive techniques to protect it with practical security analysis. Unfortunately, IoT-BLE is at risk of spoofing assaults where an attacker can pose as a gadget and provide its users a harmful information. Furthermore, due to the simplified strategy of this protocol, there were many security and privacy vulnerabilities. Justifying this quantitative security analysis with STRIDE Methodology change to create a framework to deal with protection issues for the IoT-BLE sensors. Therefore, providing probable attack scenarios for various exposures in this analysis, and offer mitigating strategies. In light of this authors performed STRIDE threat modeling to understand the attack surface for smart wearable devices supporting BLE. The study evaluates different exploitation scenarios Denial of Service (DoS), Elevation of privilege, Information disclosure, spoofing, Tampering, and repudiation on MI Band, One plus Band, Boat Storm smartwatch, and Fire Bolt Invincible.

cs.CR↗

arXiv2022

DEEPFAKE CLI: Accelerated Deepfake Detection using FPGAs

Because of the availability of larger datasets and recent improvements in the generative model, more realistic Deepfake videos are being produced each day. People consume around one billion hours of video on social media platforms every day, and thats why it is very important to stop the spread of fake videos as they can be damaging, dangerous, and malicious. There has been a significant improvement in the field of deepfake classification, but deepfake detection and inference have remained a difficult task. To solve this problem in this paper, we propose a novel DEEPFAKE C-L-I (Classification-Localization-Inference) in which we have explored the idea of accelerating Quantized Deepfake Detection Models using FPGAs due to their ability of maximum parallelism and energy efficiency compared to generalized GPUs. In this paper, we have used light MesoNet with EFF-YNet structure and accelerated it on VCK5000 FPGA, powered by state-of-the-art VC1902 Versal Architecture which uses AI, DSP, and Adaptable Engines for acceleration. We have benchmarked our inference speed with other state-of-the-art inference nodes, got 316.8 FPS on VCK5000 while maintaining 93\% Accuracy.

cs.AR↗

arXiv2021

Attacker Behaviour Profiling using Stochastic Ensemble of Hidden Markov Models

Cyber threat intelligence is one of the emerging areas of focus in information security. Much of the recent work has focused on rule-based methods and detection of network attacks using Intrusion Detection algorithms. In this paper we propose a framework for inspecting and modelling the behavioural aspect of an attacker to obtain better insight predictive power on his future actions. For modelling we propose a novel semi-supervised algorithm called Fusion Hidden Markov Model (FHMM) which is more robust to noise, requires comparatively less training time, and utilizes the benefits of ensemble learning to better model temporal relationships in data. This paper evaluates the performances of FHMM and compares it with both traditional algorithms like Markov Chain, Hidden Markov Model (HMM) and recently developed Deep Recurrent Neural Network (Deep RNN) architectures. We conduct the experiments on dataset consisting of real data attacks on a Cowrie honeypot system. FHMM provides accuracy comparable to deep RNN architectures at significant lower training time. Given these experimental results, we recommend using FHMM for modelling discrete temporal data for significantly faster training and better performance than existing methods.

cs.LG↗

arXiv2016

HMD Vision-based Teleoperating UGV and UAV for Hostile Environment using Deep Learning

The necessity of maintaining a robust antiterrorist task force has become imperative in recent times with resurgence of rogue element in the society. A well equipped combat force warrants the safety and security of citizens and the integrity of the sovereign state. In this paper we propose a novel teleoperating robot which can play a major role in combat, rescue and reconnaissance missions by substantially reducing loss of human soldiers in such hostile environments. The proposed robotic solution consists of an unmanned ground vehicle equipped with an IP camera visual system broadcasting real-time video data to a remote cloud server. With the advancement in machine learning algorithms in the field of computer vision, we incorporate state of the art deep convolutional neural networks to identify and predict individuals with malevolent intent. The classification is performed on every frame of the video stream by the trained network in the cloud server. The predicted output of the network is overlaid on the video stream with specific colour marks and prediction percentage. Finally the data is resized into half-side by side format and streamed to the head mount display worn by the human controller which facilitates first person view of the scenario. The ground vehicle is also coupled with an unmanned aerial vehicle for aerial surveillance. The proposed scheme is an assistive system and the final decision evidently lies with the human handler.

cs.RO↗