SA
Sadif Ahmed
cs.CLcs.CRcs.SEcs.AIcs.CVcs.LG
On Valency
published · living versionsW_qhggvwy7·v1 · currentpublished
When Modernization Breaks Working Code: A Single-File Study of LLMs on Legacy PHP
with Afridi Mahmud, Abid Hasan Khondaker, Md Nafiu Rahman, Rifat Shahriyar
1 version
Preprints & journals
7 papers in the corpus · 2023–2026Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents2610.23254v1 · Farhan Zarif, Kazi Shahid Ahmed Galib, Synthia Akter Promi et al.2026 · 0 citationsarXiv
Seeing Through the Forgery Is Not Enough: Regressive Sycophancy under Fabricated Evidence in Medical Vision-Language Models2610.17989v1 · Sadif Ahmed, Soumya Swagata Biswas, Rifat Shahriyar et al.2026 · 0 citationsarXiv
AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents2609.32915v1 · Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed et al.2026 · 0 citationsarXiv
IssueGuard: Real-Time Secret Leak Prevention Tool for GitHub Issue Reports2602.08072v3 · Md Nafiu Rahman, Sadif Ahmed, Zahin Wahab et al.2026 · 1 citationarXiv
BanglaForge: LLM Collaboration with Self-Refinement for Bangla Code Generation2512.19122v1 · Mahir Labib Dihan, Sadif Ahmed, Md Nafiu Rahman2025 · 0 citationsarXiv
Secret Breach Detection in Source Code with Large Language Models2504.18784v2 · Md Nafiu Rahman, Sadif Ahmed, Zahin Wahab et al.2025 · 3 citationsarXiv
Framework and Model Analysis on Bengali Document Layout Analysis Dataset: BaDLAD2309.16700v1 · Kazi Reyazul Hasan, Mubasshira Musarrat, Sadif Ahmed et al.2023 · 0 citationsarXiv
Career total: 9 works. 7 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.