arXiv subjects

Moinul Hossain

Publications and source records attributed to Moinul Hossain.

10 recordsLinked to original sources

arXiv2026

DoSQ: A Cross-Layer Denial of Service Quality Attack by Exploiting Side Channels in 5G NR

The 3rd Generation Partnership Project (3GPP)'s Fifth Generation New Radio (5G NR) is critical to supporting mission-critical services. However, 5G systems are vulnerable to smart jamming attacks that can propagate to applications running on top of these networks (i.e., cross-layer). The 5G gNB broadcasts resource scheduling information for the legitimate UEs over the air interface, with a prevailing assumption that this surface alone reveals nothing useful about a user device. However, we show that using the Downlink Control Information (DCI) is sufficient to degrade Application layer service quality, i.e., Denial of Service Quality (DoSQ), by inferring the Application layer Goodput (i.e., via side-channel analysis). Therefore, we present DoSQ, a protocol-aware attack that decodes per-slot DCI to inject interference onto the victim UE's Physical Resource Blocks (PRBs) within the same 1 ms slot, while a cross-layer classifier estimates the victim's Goodput state and trend from DCI features alone, without observing a single encrypted byte. Evaluated on a private 5G NR testbed against YouTube Live, DoSQ drives the target's Goodput down by up to 50% at sparse hit-rates, while a co-located non-target UE remains largely unaffected. Moreover, the classifier achieves a precision of 0.87 at the top 1% of attack-now confidence, a 4.21 times lift over the base rate. Furthermore, we propose an SSB frequency-time-hopping countermeasure that increases the attacker's resynchronization cost. The result is the first empirical measurement of a radio-to-application side channel that any protocol-aware adversary can exploit.

cs.CR↗

arXiv2026

FLINT: Fingerprinting Federated Learning Architectures from 5G PHY-Layer Side Channels

Federated Learning (FL) over 5G cellular networks protects raw data but remains vulnerable to side-channel leakage. Prior fingerprinting attacks assume packet-level network visibility, an assumption that does not hold at the 5G Physical (PHY) layer, where user payloads are encrypted and Radio Network Temporary Identifiers (RNTIs) may change over time. However, we demonstrate that PHY-layer scheduling metadata broadcast over the Physical Downlink Control Channel (PDCCH) preserves architecture-associated temporal patterns. We introduce FLINT, a novel black-box fingerprinting framework that infers FL model architecture families, including CNNs, RNNs, and Transformers, using only coarse PHY-layer observations. FLINT overcomes the lack of network-layer visibility by decoding PDCCH scheduling information, mapping changing RNTIs to physical user devices, and applying multi-view temporal modeling to distinguish architecture-specific training behavior. This leakage is security-critical because knowledge of a client's model architecture can transform passive reconnaissance into targeted downstream exploitation. Extensive experiments on an over-the-air srsRAN-based 5G testbed demonstrate that FLINT achieves a macro F1-score of 0.930 for architecture-family classification. To our knowledge, FLINT is the first work to fingerprint AI/ML model architectures using lower-layer 5G side-channel information obtainable by any protocol-aware adversary.

cs.CR↗

arXiv2026

Towards Intelligent Legal Document Analysis: CNN-Driven Classification of Case Law Texts

Legal practitioners and judicial institutions face an ever-growing volume of case-law documents characterised by formalised language, lengthy sentence structures, and highly specialised terminology, making manual triage both time-consuming and error-prone. This work presents a lightweight yet high-accuracy framework for citation-treatment classification that pairs lemmatisation-based preprocessing with subword-aware FastText embeddings and a multi-kernel one-dimensional Convolutional Neural Network (CNN). Evaluated on a publicly available corpus of 25,000 annotated legal documents with a 75/25 training-test partition, the proposed system achieves 97.26% classification accuracy and a macro F1-score of 96.82%, surpassing established baselines including fine-tuned BERT, Long Short-Term Memory (LSTM) with FastText, CNN with random embeddings, and a Term Frequency-Inverse Document Frequency (TF-IDF) k-Nearest Neighbour (KNN) classifier. The model also attains the highest Area Under the Receiver Operating Characteristic (AUC-ROC) curve of 97.83% among all compared systems while operating with only 5.1 million parameters and an inference latency of 0.31 ms per document - more than 13 times faster than BERT. Ablation experiments confirm the individual contribution of each pipeline component, and the confusion matrix reveals that residual errors are confined to semantically adjacent citation categories. These findings indicate that carefully designed convolutional architectures represent a scalable, resource-efficient alternative to heavyweight transformers for intelligent legal document analysis.

cs.CL↗

arXiv2026

Analyzing the Impact of Adversarial Attacks on C-V2X-Enabled Road Safety: An Age of Information Perspective

The Cellular Vehicle-to-Everything (C-V2X), introduced and developed by the 3GPP, is a promising technology for the Autonomous Driving System (ADS). C-V2X aims to fulfill the Service-Level Requirements (SLRs) of ADS to ensure road safety following the development of the latest version, i.e., the NR-V2X. However, vulnerabilities threatening road safety in NR-V2X persist that have yet to be investigated. Existing research primarily evaluates road safety based on successful packet receptions. In this work, we propose a novel resource starvation attack that exploits vulnerabilities in the resource allocation of NR-V2X to diminish the required SLRs, making the road condition unsafe for autonomous driving. Furthermore, we establish the Age of Information (AoI) as the predominant metric for estimating the impact of adversarial attacks on NR-V2X by constructing a Discrete-time Markov chain (DTMC) based analytical model and validating it through extensive simulations. Finally, our analysis underscores how the proposed attack on NR-V2X can lead to unsafe driving conditions by reducing the SLR of time-sensitive applications in ADS up to 15% from the target. Additionally, we observe that even benign vehicles act selfishly when resources are scarce, leading to further safety compromises.

cs.CR↗

arXiv2025

PHANTOM: PHysical ANamorphic Threats Obstructing Connected Vehicle Mobility

Connected autonomous vehicles (CAVs) rely on vision-based deep neural networks (DNNs) and low-latency (Vehicle-to-Everything) V2X communication to navigate safely and efficiently. Despite their advances, these systems remain vulnerable to physical adversarial attacks. In this paper, we introduce PHANTOM (PHysical ANamorphic Threats Obstructing connected vehicle Mobility), a novel framework for crafting and deploying perspective-dependent adversarial examples using \textit{anamorphic art}. PHANTOM exploits geometric distortions that appear natural to humans but are misclassified with high confidence by state-of-the-art object detectors. Unlike conventional attacks, PHANTOM operates in black-box settings without model access and demonstrates strong transferability across four diverse detector architectures (YOLOv5, SSD, Faster R-CNN, and RetinaNet). Comprehensive evaluation in CARLA across varying speeds, weather conditions, and lighting scenarios shows that PHANTOM achieves over 90\% attack success rate under optimal conditions and maintains 60-80\% effectiveness even in degraded environments. The attack activates within 6-10 meters of the target, providing insufficient time for safe maneuvering. Beyond individual vehicle deception, PHANTOM triggers network-wide disruption in CAV systems: SUMO-OMNeT++ co-simulation demonstrates that false emergency messages propagate through V2X links, increasing Peak Age of Information by 68-89\% and degrading safety-critical communication. These findings expose critical vulnerabilities in both perception and communication layers of CAV ecosystems.

cs.CV↗

arXiv2025

FLARE: A Wireless Side-Channel Fingerprinting Attack on Federated Learning

Federated Learning (FL) enables collaborative model training across distributed devices while safeguarding data and user privacy. However, FL remains susceptible to privacy threats that can compromise data via direct means. That said, indirectly compromising the confidentiality of the FL model architecture (e.g., a convolutional neural network (CNN) or a recurrent neural network (RNN)) on a client device by an outsider remains unexplored. If leaked, this information can enable next-level attacks tailored to the architecture. This paper proposes a novel side-channel fingerprinting attack, leveraging flow-level and packet-level statistics of encrypted wireless traffic from an FL client to infer its deep learning model architecture. We name it FLARE, a fingerprinting framework based on FL Architecture REconnaissance. Evaluation across various CNN and RNN variants-including pre-trained and custom models trained over IEEE 802.11 Wi-Fi-shows that FLARE achieves over 98% F1-score in closed-world and up to 91% in open-world scenarios. These results reveal that CNN and RNN models leak distinguishable traffic patterns, enabling architecture fingerprinting even under realistic FL settings with hardware, software, and data heterogeneity. To our knowledge, this is the first work to fingerprint FL model architectures by sniffing encrypted wireless traffic, exposing a critical side-channel vulnerability in current FL systems.

cs.CR↗

arXiv2025

Revisiting Classical Two-phase and Kerner Three-phase Traffic Flow Theories: A Comparison of Pre-crash and Normal Traffic Conditions

Extensive research has been conducted to develop statistical and artificial intelligence-based models for predicting short-term crash probabilities using fundamental traffic flow variables and their associated descriptive statistics and mathematical transformations. However, there has been limited exploration into whether and how the fundamental relationships within traffic flow theories vary between pre-crash and normal traffic conditions. This study reevaluates four classical two-phase traffic flow theories and employs two methods from Kerner's three-phase traffic flow theory to compare their characteristics in the context of pre-crash and normal traffic conditions. The investigation is centered around the Shibuya 3 and Shinjuku 4 routes within the Tokyo Metropolitan Expressway. Data from both crashes and detectors was collected over a six-month period, spanning from March 2014 to August 2014. The findings reveal that data from the nearest downstream detectors to the crash locations provided a superior fit for pre-crash data compared to the upstream detectors. Notably, a noticeable decrease in goodness-of-fit was observed when compared to normal traffic conditions. In pre-crash scenarios, wide-moving jams exhibited a faster propagation from downstream to upstream, distinct from the patterns observed in normal traffic conditions. Furthermore, pre-crash data displayed a higher standard deviation in the calculated wide-moving jam velocities compared to normal traffic conditions. These insights have the potential to be highly valuable in the development of predictive crash models and in the estimation of traffic volumes on freeways across various timeframes, accounting for both free-flow and congested traffic scenarios.

physics.soc-ph↗

arXiv2025

Fingerprinting Deep Learning Models via Network Traffic Patterns in Federated Learning

Federated Learning (FL) is increasingly adopted as a decentralized machine learning paradigm due to its capability to preserve data privacy by training models without centralizing user data. However, FL is susceptible to indirect privacy breaches via network traffic analysis-an area not explored in existing research. The primary objective of this research is to study the feasibility of fingerprinting deep learning models deployed within FL environments by analyzing their network-layer traffic information. In this paper, we conduct an experimental evaluation using various deep learning architectures (i.e., CNN, RNN) within a federated learning testbed. We utilize machine learning algorithms, including Support Vector Machines (SVM), Random Forest, and Gradient-Boosting, to fingerprint unique patterns within the traffic data. Our experiments show high fingerprinting accuracy, achieving 100% accuracy using Random Forest and around 95.7% accuracy using SVM and Gradient Boosting classifiers. This analysis suggests that we can identify specific architectures running within the subsection of the network traffic. Hence, if an adversary knows about the underlying DL architecture, they can exploit that information and conduct targeted attacks. These findings suggest a notable security vulnerability in FL systems and the necessity of strengthening it at the network level.

cs.LG↗

arXiv2023

PACMAN Attack: A Mobility-Powered Attack in Private 5G-Enabled Industrial Automation System

3GPP has introduced Private 5G to support the next-generation industrial automation system (IAS) due to the versatility and flexibility of 5G architecture. Besides the 3.5GHz CBRS band, unlicensed spectrum bands, like 5GHz, are considered as an additional medium because of their free and abundant nature. However, while utilizing the unlicensed band, industrial equipment must coexist with incumbents, e.g., Wi-Fi, which could introduce new security threats and resuscitate old ones. In this paper, we propose a novel attack strategy conducted by a mobility-enabled malicious Wi-Fi access point (mmAP), namely \textit{PACMAN} attack, to exploit vulnerabilities introduced by heterogeneous coexistence. A mmAP is capable of moving around the physical surface to identify mission-critical devices, hopping through the frequency domain to detect the victim's operating channel, and launching traditional MAC layer-based attacks. The multi-dimensional mobility of the attacker makes it impervious to state-of-the-art detection techniques that assume static adversaries. In addition, we propose a novel Markov Decision Process (MDP) based framework to intelligently design an attacker's multi-dimensional mobility in space and frequency. Mathematical analysis and extensive simulation results exhibit the adverse effect of the proposed mobility-powered attack.

cs.CR↗

arXiv2022

Intent-Aware Permission Architecture: A Model for Rethinking Informed Consent for Android Apps

As data privacy continues to be a crucial human-right concern as recognized by the UN, regulatory agencies have demanded developers obtain user permission before accessing user-sensitive data. Mainly through the use of privacy policies statements, developers fulfill their legal requirements to keep users abreast of the requests for their data. In addition, platforms such as Android enforces explicit permission request using the permission model. Nonetheless, recent research has shown that service providers hardly make full disclosure when requesting data in these statements. Neither is the current permission model designed to provide adequate informed consent. Often users have no clear understanding of the reason and scope of usage of the data request. This paper proposes an unambiguous, informed consent process that provides developers with a standardized method for declaring Intent. Our proposed Intent-aware permission architecture extends the current Android permission model with a precise mechanism for full disclosure of purpose and scope limitation. The design of which is based on an ontology study of data requests purposes. The overarching objective of this model is to ensure end-users are adequately informed before making decisions on their data. Additionally, this model has the potential to improve trust between end-users and developers.

cs.CY↗