arXiv subjects

Istiaq Ahmed Fahad

Publications and source records attributed to Istiaq Ahmed Fahad.

4 recordsLinked to original sources

arXiv2026

Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts

Large Language Models (LLMs) are increasingly used for code smell detection tasks due to their ability to interpret program semantics. However, their reliability in this context remains poorly explored, particularly under varying prompt conditions where model predictions may be influenced by external cues rather than code characteristics. One such limitation is sycophancy bias, where models tend to align their outputs with user-provided assumptions instead of performing objective analysis. In this paper, we present the first systematic empirical study of sycophancy bias in LLM-based code smell detection. Using the MLCQ dataset, we evaluate how different prompt framings like confirmation bias, contradictory hints, and false premises affect model predictions. Our results show that LLMs are highly sensitive to prompt variations, with Decision Flip Rates reaching up to 72% and False Alignment Rates exceeding 90%, indicating substantial instability and agreement with misleading prompts. To address this issue, we propose Evidence-Guided Debiasing Prompting (EGDP), a structured prompting strategy that enforces evidence-first reasoning. EGDP reduces decision instability and improves robustness, lowering Decision Flip Rates to as low as 12% and False Alignment Rates to as low as 21%, while increasing reliance on structurally grounded evidence. Our findings demonstrate that sycophancy bias poses a critical threat to the reliability of LLM-based code smell detection, and that evidence-guided reasoning provides an effective and generalizable mitigation approach.

cs.SE↗

arXiv2026

PromptMark: A Prompt-Guided Iterative-Feedback Framework for Source Code Watermarking

Watermarking has become a crucial technique for ensuring provenance and accountability in AI-generated source code. As large language models (LLMs) are increasingly integrated into development workflows, reliable attribution remains challenging. In practice, most developers rely on commercial LLM APIs operating under black-box constraints, making existing approaches that require access to the decoding process less feasible for real-world integration. To address this limitation, we propose PromptMark, a black-box, prompt-guided watermarking framework that embeds invisible yet statistically detectable signals into generated code via structured input instructions. The method steers models toward subtle identifier and comment naming patterns while preserving the functional correctness and structural integrity of the generated code. Detection is performed using statistical tests designed to remain reliable across varying code lengths and model outputs. The embedding is further refined through an iterative feedback loop, where prompts are updated based on watermark detection scores. Experiments on the MBPP and HumanEval benchmarks show that PromptMark consistently achieves strong watermark detectability while maintaining high code correctness, outperforming baseline approaches.

cs.CR↗

arXiv2025

BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset

Deepfake audio detection is challenging for low-resource languages like Bengali due to limited datasets and subtle acoustic features. To address this, we introduce BangalFake, a Bengali Deepfake Audio Dataset with 12,260 real and 13,260 deepfake utterances. Synthetic speech is generated using SOTA Text-to-Speech (TTS) models, ensuring high naturalness and quality. We evaluate the dataset through both qualitative and quantitative analyses. Mean Opinion Score (MOS) from 30 native speakers shows Robust-MOS of 3.40 (naturalness) and 4.01 (intelligibility). t-SNE visualization of MFCCs highlights real vs. fake differentiation challenges. This dataset serves as a crucial resource for advancing deepfake detection in Bengali, addressing the limitations of low-resource language research.

cs.SD↗

arXiv2025

Automatic Vehicle Detection using DETR: A Transformer-Based Approach for Navigating Treacherous Roads

Automatic Vehicle Detection (AVD) in diverse driving environments presents unique challenges due to varying lighting conditions, road types, and vehicle types. Traditional methods, such as YOLO and Faster R-CNN, often struggle to cope with these complexities. As computer vision evolves, combining Convolutional Neural Networks (CNNs) with Transformer-based approaches offers promising opportunities for improving detection accuracy and efficiency. This study is the first to experiment with Detection Transformer (DETR) for automatic vehicle detection in complex and varied settings. We employ a Collaborative Hybrid Assignments Training scheme, Co-DETR, to enhance feature learning and attention mechanisms in DETR. By leveraging versatile label assignment strategies and introducing multiple parallel auxiliary heads, we provide more effective supervision during training and extract positive coordinates to boost training efficiency. Through extensive experiments on DETR variants and YOLO models, conducted using the BadODD dataset, we demonstrate the advantages of our approach. Our method achieves superior results, and improved accuracy in diverse conditions, making it practical for real-world deployment. This work significantly advances autonomous navigation technology and opens new research avenues in object detection for autonomous vehicles. By integrating the strengths of CNNs and Transformers, we highlight the potential of DETR for robust and efficient vehicle detection in challenging driving environments.

cs.CV↗