Case study 01 / Multimodal AI · Industry internship
Truuth Document Forensics Pipeline
Finding the edits a vision model missed.
All 40 modified documents detected in the final evaluation, with zero false positives.
DOCUMENT
System-level fix.
01 / Context
Problem
Document tampering can be visually subtle. A small modified region can disappear inside an otherwise plausible page, making document-level multimodal inference an unreliable signal on its own.
The pipeline needed to combine complementary evidence and track both missed modifications and false alarms as the approach evolved.
02 / Ownership
My Role
As an AI Engineer Intern at Truuth, I built a Python document-forensics pipeline using Error Level Analysis heatmaps, PDF structural analysis and Qwen3-VL-235B through the AWS Bedrock Converse API, with a RAG component.
I automated benchmarking across 12 versions, tracked false positives and false negatives as regression tests, investigated model failure and wrote R&D handover documentation. The internship concluded in June 2026.
03 / System design
Architecture
- 01Document input
Document images and PDFs
- 02Forensic signals
ELA heatmaps + PDF structural analysis
- 03Multimodal reasoning
Qwen3-VL-235B · Bedrock Converse · RAG component
- 04Decision & evaluation
Decision logic + versioned regression checks
04 / Engineering decisions
What Went Wrong & How I Fixed It
The signal was getting lost before the prompt could help.
The vision encoder’s patch averaging diluted fine-grained tampering signals. Small edits were being blended into the surrounding page representation.
I changed the inputs and the decision logic rather than relying only on prompt changes. This addressed the information reaching the model and how the pipeline used the evidence.
Automated evaluation across 12 versions made regressions visible. The debugging lesson: inspect the representation and the surrounding system when a model misses a small but important signal.
05 / Evidence
Results
These are the supplied final evaluation results, not a claim of universal accuracy. The number of genuine control documents and the full evaluation protocol have not been supplied. Specificity and overall accuracy are therefore not calculated.
06 / Tools & capabilities
Stack
07 / Explore further
Links
Industry project. Employer code and documents are not published here. I can discuss the engineering approach using non-confidential examples.