Ali Hussain

B.S. Computer Science, NUST (2023 – 2027)

Islamabad, Pakistan

ahussain.bscs23seecs@seecs.edu.pk

I am a final-year Computer Science undergraduate at the National University of Sciences and Technology (NUST), Pakistan, and I am looking for a PhD position starting Fall 2027.

My research asks one question from several angles: what do visual models actually learn, and how can we make them learn the right thing when data, compute, or trust are limited? So far I have explored this in three settings:

Adding a missing signal. In low-resource online handwriting, I turned pen dynamics (pressure, velocity, direction, tilt) into image channels. This let a pretrained offline recognizer use them without training a sequence model from scratch. (first author, ICDAR 2026)
Removing a misleading signal. State-of-the-art document-forgery detectors turn out to rely on the JPEG 8×8 compression grid rather than on the edit itself. We built two simple, query-free attacks that expose this. (equal-contribution first author, BMVC 2026)
Compressing a signal. In ongoing work, I study how to distill large vision foundation models into compact students that run on edge hardware, measured on a real Raspberry Pi under power constraints.

I have worked with Prof. Faisal Shafait at NUST, with Prof. Andreas Dengel and Dr. Sheraz Ahmed at DFKI, and with Dr. Christian Weis at RPTU Kaiserslautern-Landau.

Research interests

I am deliberately broad at this stage. I would be excited to continue in any of these directions, or in a focused niche within them:

Visual representation learning and robust computer vision: shortcut learning, inductive biases, and failure-mode analysis
Multimodal learning: fusing heterogeneous signals (vision, trajectories, frequency, language) into shared representations
Efficient foundation models: knowledge distillation and parameter-efficient adaptation for deployment under compute and energy budgets
Reinforcement learning for task-driven image generation: adapting generative models toward downstream objectives such as robustness evaluation
Document intelligence and handwriting recognition, especially for low-resource scripts such as Urdu

I care about careful experimental practice: multiple seeds, significance tests, controlled ablations, and public code and data. Recently I have also been building tools to make my own research on HPC clusters more reproducible.

Outside research, I work part-time as a computer vision engineer at CCRIPT. There I take detection and tracking models from experiment to deployment on constrained hardware.

selected publications

ICDAR
Online Urdu Text-Line Recognition by Bridging Stroke Dynamics and Offline Representations

Ali Hussain, Rafay Ahmad, Momina Moetesum, Adnan Ul-Hasan, and Faisal Shafait

In International Conference on Document Analysis and Recognition (ICDAR). Dataset: OUHD-L on Zenodo , 2026

Abs Bib PDF Code

Robust recognition of Urdu has been challenging due to its cursive structure and extensive ligature variations. Modern pen devices capture rich spatio-temporal signals; however, state-of-the-art Urdu research predominantly focuses on offline images, and online-first transformer and vision-language approaches overfit in low-resource settings. We present two contributions: (i) OUHD-L, a new dataset of 2,403 online Urdu handwritten text lines from 311 writers, captured with the Wacom IoT paper device at fine-grained pen-trajectory resolution; and (ii) an encoding of online information as image channels that lets us reuse pre-trained offline Urdu text-line recognizers. Fusing online-derived feature images reduces character error rate from 4.21% (ink-only) to 3.66%, showing that converting online dynamics into image space bridges the data gap while reusing mature offline architectures.
@inproceedings{hussain2026online, title = {Online Urdu Text-Line Recognition by Bridging Stroke Dynamics and Offline Representations}, author = {Hussain, Ali and Ahmad, Rafay and Moetesum, Momina and Ul-Hasan, Adnan and Shafait, Faisal}, booktitle = {International Conference on Document Analysis and Recognition (ICDAR)}, year = {2026}, }
BMVC
Mistaking Periodicity for Manipulation: JPEG-Induced Structural Bias in Document Tampering Detection

Nauman Riaz^*, Ali Hussain^*, Saifullah Saifullah^*, Muhammad Imran Malik, Stefan Agne, Andreas Dengel, and Sheraz Ahmed

In British Machine Vision Conference (BMVC), 2026

Abs Bib PDF

Deep models for document tampering detection increasingly rely on multimodal RGB+DCT architectures, implicitly assuming that JPEG block artifact grids (BAGs) provide stable cross-forgery cues. We show that this assumption embeds a strong inductive bias that fails under minimal, adversarially constructed perturbations. Unlike natural images, document images contain sharply bounded glyph structures, making grid-aligned manipulations trivial for an adversary. We formalize this through two complementary attacks. Grid-Aligned Forgery (GAF) preserves local JPEG block statistics by aligning copy-move, splicing, or generative manipulations to the 8x8 grid. Pad-Recompress-Crop (PRC) globally shifts the JPEG grid while preserving semantic content and geometry. We introduce Detection Failure Rate (DFR) and False Positive Area (FPA) to capture failure modes not measured by prior work. On DocTamper and T-SROIE, both attacks substantially degrade state-of-the-art and robustness-oriented detectors (CAT-Net, DTD, FFDN, DocForgeNet, ADCD-Net), indicating a strong bias toward JPEG-grid statistics.
@inproceedings{riaz2026periodicity, title = {Mistaking Periodicity for Manipulation: JPEG-Induced Structural Bias in Document Tampering Detection}, author = {Riaz, Nauman and Hussain, Ali and Saifullah, Saifullah and Malik, Muhammad Imran and Agne, Stefan and Dengel, Andreas and Ahmed, Sheraz}, booktitle = {British Machine Vision Conference (BMVC)}, year = {2026}, }

news

Sep 05, 2026	Completed my research internship at RPTU Kaiserslautern-Landau (8 Jun – 5 Sep 2026). The distillation work continues as my final-year project.
Aug 31, 2026	My first-author paper on online Urdu text-line recognition appears at ICDAR 2026 in Vienna. Code and the OUHD-L dataset are public.
Aug 07, 2026	Our paper Mistaking Periodicity for Manipulation was accepted at BMVC 2026. We show that document-tampering detectors rely on the JPEG 8×8 grid, and we introduce two attacks that break them.
Jun 08, 2026	Started a research internship at RPTU Kaiserslautern-Landau with Dr. Christian Weis on foundation-model distillation for edge inference.
Aug 31, 2025	Wrapped up my research internship at DFKI (1 Jun – 31 Aug 2025). This work led to our BMVC 2026 paper on JPEG-induced bias in document tampering detection.
Jun 01, 2025	Started a research internship at DFKI in Kaiserslautern, Germany, on document image forensics with Prof. Andreas Dengel and Dr. Sheraz Ahmed.
Jun 01, 2024	Joined the TUKL-NUST R&D Center as an undergraduate researcher working on handwriting recognition with Prof. Faisal Shafait.