arXiv subjects

Tanvir Hossain

Publications and source records attributed to Tanvir Hossain.

11 recordsLinked to original sources

arXiv2026

GlitchLab: A Hardware-in-the-Loop Optimizer for Physical Fault Injection

Physical fault injection can turn brief hardware disturbances into security failures such as key recovery, authentication bypass, and unintended control flow. Finding effective faults is difficult because many interacting parameters create a large search space, successful settings are sparse and target-dependent, and each hardware attempt provides limited feedback. Under fixed testing time, efficient search is therefore critical for assessing fault sensitivity. We present GlitchLab, an online hardware-in-the-loop platform that treats delay as a timing gate, voltage and pulse duration as severity controls, and hardware outcomes as structured feedback. It implements RL-Q (Q-learning-based reinforcement learning), a structured bandit for discovery, and Structured-Outcome-Based Adaptive Search (SOBAS), a model-based policy for fault reproduction. Both policies find a target fault in every AES, password, and control-flow campaign. On AES and control flow, they require 2-85x fewer attempts and 26-1,237x less time than the baselines; on password, both succeed while the baselines fail within 5,000 attempts. After discovery, SOBAS reproduces faults 7.3-21x more often, while RL-Q identifies 30% more distinct AES settings.

cs.CR↗

arXiv2026

Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs

Graph neural networks (GNNs) have achieved strong performance across various real-world domains. Nevertheless, they suffer from oversquashing, where long-range information is distorted as it is compressed through limited message-passing pathways. This bottleneck limits their ability to capture essential global context and decreases their performance, particularly in dense and heterophilic regions of graphs. To address this issue, we propose a novel graph learning framework that enriches node embeddings via cross-attentive cohesive subgraph representations to mitigate the impact of excessive long-range dependencies. This framework enhances the node representation by emphasizing cohesive structure in long-range information but removing noisy or irrelevant connections. It preserves essential global context without overloading the narrow bottlenecked channels, which further mitigates oversquashing. Extensive experiments on multiple benchmark datasets demonstrate that our model achieves consistent improvements in classification accuracy over standard baseline methods.

cs.LG↗

arXiv2026

Bengali-Loop: Community Benchmarks for Long-Form Bangla ASR and Speaker Diarization

Bengali (Bangla) remains under-resourced in long-form speech technology despite its wide use. We present Bengali-Loop, two community benchmarks to address this gap: (1) a long-form ASR corpus of 191 recordings (158.6 hours, 792k words) from 11 YouTube channels, collected via a reproducible subtitle-extraction pipeline and human-in-the-loop transcript verification; and (2) a speaker diarization corpus of 24 recordings (22 hours, 5,744 annotated segments) with fully manual speaker-turn labels in CSV format. Both benchmarks target realistic multi-speaker, long-duration content (e.g., Bangla drama/natok). We establish baselines (Tugstugi: 34.07% WER; pyannote.audio: 40.08% DER) and provide standardized evaluation protocols (WER/CER, DER), annotation rules, and data formats to support reproducible benchmarking and future model development for Bangla long-form ASR and diarization.

cs.SD↗

arXiv2024

A Persistent Hierarchical Bloom Filter-based Framework for Authentication and Tracking of ICs

Detecting counterfeit integrated circuits (ICs) in unreliable supply chains demands robust tracking and authentication. Physical Unclonable Functions (PUFs) offer unique IC identifiers, but noise undermines their utility. This study introduces the Persistent Hierarchical Bloom Filter (PHBF) framework, ensuring swift and accurate IC authentication with an accuracy rate of 100% across the supply chain even with noisy PUF-generated signatures.

cs.CR↗

arXiv2024

Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach

Graph Neural Network (GNN) achieves great success for node-level and graph-level tasks via encoding meaningful topological structures of networks in various domains, ranging from social to biological networks. However, repeated aggregation operations lead to excessive mixing of node representations, particularly in dense regions with multiple GNN layers, resulting in nearly indistinguishable embeddings. This phenomenon leads to the oversmoothing problem that hampers downstream graph analytics tasks. To overcome this issue, we propose a novel and flexible truss-based graph sparsification model that prunes edges from dense regions of the graph. Pruning redundant edges in dense regions helps to prevent the aggregation of excessive neighborhood information during hierarchical message passing and pooling in GNN models. We then utilize our sparsification model in the state-of-the-art baseline GNNs and pooling models, such as GIN, SAGPool, GMT, DiffPool, MinCutPool, HGP-SL, DMonPool, and AdamGNN. Extensive experiments on different real-world datasets show that our model significantly improves the performance of the baseline GNN models in the graph classification task.

cs.LG↗

arXiv2024

DyGCL: Dynamic Graph Contrastive Learning For Event Prediction

Predicting events such as political protests, flu epidemics, and criminal activities is crucial to proactively taking necessary measures and implementing required responses to address emerging challenges. Capturing contextual information from textual data for event forecasting poses significant challenges due to the intricate structure of the documents and the evolving nature of events. Recently, dynamic Graph Neural Networks (GNNs) have been introduced to capture the dynamic patterns of input text graphs. However, these models only utilize node-level representation, causing the loss of the global information from graph-level representation. On the other hand, both node-level and graph-level representations are essential for effective event prediction as node-level representation gives insight into the local structure, and the graph-level representation provides an understanding of the global structure of the temporal graph. To address these challenges, in this paper, we propose a Dynamic Graph Contrastive Learning (DyGCL) method for event prediction. Our model DyGCL employs a local view encoder to learn the evolving node representations, which effectively captures the local dynamic structure of input graphs. Additionally, it harnesses a global view encoder to perceive the hierarchical dynamic graph representation of the input graphs. Then we update the graph representations from both encoders using contrastive learning. In the final stage, DyGCL combines both representations using an attention mechanism and optimizes its capability to predict future events. Our extensive experiment demonstrates that our proposed method outperforms the baseline methods for event prediction on six real-world datasets.

cs.SI↗

arXiv2024

HOACS: Homomorphic Obfuscation Assisted Concealing of Secrets to Thwart Trojan Attacks in COTS Processor

Commercial-off-the-shelf (COTS) components are often preferred over custom Integrated Circuits (ICs) to achieve reduced system development time and cost, easy adoption of new technologies, and replaceability. Unfortunately, the integration of COTS components introduces serious security concerns. None of the entities in the COTS IC supply chain are trusted from a consumer's perspective, leading to a ''zero trust'' threat model. Any of these entities could introduce hidden malicious circuits or hardware Trojans within the component, allowing an attacker in the field to extract secret information (e.g., cryptographic keys) or cause a functional failure. Existing solutions to counter hardware Trojans are inapplicable in such a zero-trust scenario as they assume either the design house or the foundry to be trusted and consider the design to be available for either analysis or modification. In this work, we have proposed a software-oriented countermeasure to ensure the confidentiality of secret assets against hardware Trojans that can be seamlessly integrated in existing COTS microprocessors. The proposed solution does not require any supply chain entity to be trusted and does not require analysis or modification of the IC design. To protect secret assets in an untrusted microprocessor, the proposed method leverages the concept of residue number coding (RNC) to transform the software functions operating on the asset to be fully homomorphic. We have implemented the proposed solution to protect the secret key within the Advanced Encryption Standard (AES) program and presented a detailed security analysis. We also have developed a plugin for the LLVM compiler toolchain that automatically integrates the solution in AES. Finally, we compare the execution time overhead of the operations in the RNC-based technique with comparable homomorphic solutions and demonstrate significant improvement.

cs.CR↗

arXiv2023

HeTriNet: Heterogeneous Graph Triplet Attention Network for Drug-Target-Disease Interaction

Modeling the interactions between drugs, targets, and diseases is paramount in drug discovery and has significant implications for precision medicine and personalized treatments. Current approaches frequently consider drug-target or drug-disease interactions individually, ignoring the interdependencies among all three entities. Within human metabolic systems, drugs interact with protein targets in cells, influencing target activities and subsequently impacting biological pathways to promote healthy functions and treat diseases. Moving beyond binary relationships and exploring tighter triple relationships is essential to understanding drugs' mechanism of action (MoAs). Moreover, identifying the heterogeneity of drugs, targets, and diseases, along with their distinct characteristics, is critical to model these complex interactions appropriately. To address these challenges, we effectively model the interconnectedness of all entities in a heterogeneous graph and develop a novel Heterogeneous Graph Triplet Attention Network (\texttt{HeTriNet}). \texttt{HeTriNet} introduces a novel triplet attention mechanism within this heterogeneous graph structure. Beyond pairwise attention as the importance of an entity for the other one, we define triplet attention to model the importance of pairs for entities in the drug-target-disease triplet prediction problem. Experimental results on real-world datasets show that \texttt{HeTriNet} outperforms several baselines, demonstrating its remarkable proficiency in uncovering novel drug-target-disease relationships.

cs.LG↗

arXiv2022

Energy and Time Based Topology Control Approach to Enhance the Lifetime of WSN in an economic zone

An economic zone requires continuous monitoring and controlling by an autonomous surveillance system for heightening its production competency and security. Wireless sensor network (WSN) has swiftly grown popularity over the world for uninterruptedly monitoring and controlling a system. Sensor devices, the main elements of WSN, are given limited amount of energy, which leads the network to limited lifespan. Therefore, the most significant challenge is to increase the lifespan of a WSN system. Topology control mechanism (TCM) is a renowned method to enhance the lifespan of WSN. This paper proposes an approach to extend the lifetime of WSN for an economic area, targeting an economic zone in Bangladesh. Observations are made on the performance of the network lifetime considering the individual combinations of the TCM protocols and comparative investigation between the time and energy triggering strategy of TCM protocols. Results reveal the network makes a better performance in the case of A3 protocol while using the topology maintenance protocols with both time and energy triggering methods. Moreover, the performance of the A3 and DGETRec is superior to the other combinations of TCM protocols. Hence, the WSN system can be able to serve better connectivity coverage in the target economic zone.

cs.NI↗

arXiv2020

Mobility in immersed granular materials upon cyclic loading

We study the mobility of objects embedded in an immersed granular packing and subjected to cyclic loadings. In this aim, we conducted experiments using glass beads immersed in water and a horizontal plate subjected to a cyclic uplift force. Tests performed at different cyclic force frequencies and amplitudes evidence the development of three mobility regimes whereby the plate stays virtually immobile, moves up steadily or slowly creeps upwards. Results show that steady plate uplift can occur at lower force magnitudes when the frequency is increased. We propose an interpretation of this frequency-weakening behaviour based on force relaxation experiments and on the analysis of the mobility response of theoretical visco-elasto-plastic mechanical analogue. These results and analysis point out inherent differences in mobility response between steady and cyclic loadings in immersed granular materials.

cond-mat.soft↗

arXiv2020

Drag force in immersed granular materials

We investigate the drag forces acting on large objects moving through a granular packing immersed in water. In this aim, we conducted uplift experiments involving pulling out horizontal plates at a prescribed velocity vertically. During these tests, we observed that the drag force reaches to peak at a low displacement and then decays. Results show that the peak drag force strongly increases with the velocity and depends on the plate size and grain diameter. We identify empirical scaling laws for these properties and introduce a Darcy-flow mechanism that can explain them. Furthermore, we conducted tests involving suddenly stopping the motion of the plate, which evidenced a progressive relaxation of the drag force in time. We discuss how a visco-elasto-plastic mechanical analogue can reproduce these dynamics. These results and analyses highlight fundamental differences in drag force between dry and immersed granular materials.

cond-mat.soft↗