Update September Project of the Month

profile/README.md

@@ -18,19 +18,19 @@
 ---
 
 <div align="center">
-  <img src="./august.jpeg" alt="Happy August Meme" style="width: 50%; height: auto;">
+  <img src="./september.png" alt="Happy September Meme" style="width: 50%; height: auto;">
   <br><br>IEEE offers a range of exciting projects across diverse disciplines, ready for your innovative touch in 2026! 🥳
 </div>
 <br>
 <div align="center">
-  <b>August @ IEEE VIT is about depth, discipline, and building things that matter.</b>
+  <b>September @ IEEE VIT is about depth, discipline, and building things that matter.</b>
 </div>
 
 <div align="center">
   <br>
   Sharper execution, cleaner systems, and code that holds up under pressure. Less noise. More signal. Real ownership.</br>
 
-  <br>August is not about doing more.</br>
+  <br>September is not about doing more.</br>
   This isn't a sprint month. It's an ownership month.  
   The kind where you stay on the bug past the point of curiosity, where the architecture gets questioned before it gets built, where "good enough" isn't in the vocabulary. Small, deliberate, relentless.
 </div>
@@ -45,40 +45,53 @@
 
 <div align='center'>
 
-  <a href="https://www.youtube.com/watch?v=ZhIsAZO5gl0" target="_blank">🐞</a>
+  <a href="https://youtu.be/F-6OLCvO7MA?si=M3tgj-xOAYacya0e" target="_blank">🐞</a>
 </div>
 
 <div align="center">
- <h2>August's Project of the Month</h2>
+ <h2>September's Project of the Month</h2>
 
   <b>
-    <a href="https://github.com/IEEE-VIT/FL_Powered_Medical_AI">FLAIM</a>
+    <a href="https://github.com/IEEE-VIT/FL_Powered_Medical_AI">ProofStamp</a>
   </b>
 
-  <br>
-  FLAIM is a federated learning framework that lets multiple hospitals collaboratively train a chest X-ray diagnosis model without sharing patient data. Each hospital trains locally on its own dataset and shares only model updates. These updates are combined into a global model using Federated Averaging (FedAvg). Patient images never leave the hospital where they were collected.
+ <br>
 
-  The core architectural decision is the split between local computation and global knowledge: each hospital node runs its own training pipeline and differential privacy module on premises, and only noised, clipped model weights are transmitted. Raw data stays siloed while the aggregator still produces a model trained on the collective signal from every node.
-  </br>
-  <br>
+ProofStamp is a legal-tech platform that gives Indian content creators verifiable proof of ownership for their digital work. Creators can upload photographs, illustrations, documents, scripts, audio, video, and other digital files and receive a cryptographically secured Proof Passport. The platform combines identity binding, SHA-256 hashing, RSA signatures, trusted timestamps, invisible watermarking, blockchain anchoring, and digital evidence generation to establish the existence, integrity, and ownership context of a work while keeping the original content private.
+
+</div>
+
+<br>
 
 ## Features
 
-* **Federated Learning core:** A Flower based framework coordinates training across hospital nodes using the FedAvg aggregation strategy. Each node trains locally on its own partition of the PadChest dataset.
-* **Differential Privacy:** Opacus handles per sample gradient clipping and noise injection before parameters are shared. Privacy budget (ε) is tracked and logged for every round.
-* **DenseNet121 transfer learning:** An ImageNet pretrained DenseNet121 backbone is fine tuned on chest X-ray data, with `denseblock4`, `norm5`, and `classifier` layers unfrozen for training. This allows fast convergence even with limited per hospital data.
-* **Byzantine detection support:** Aggregation level anomaly detection hooks flag suspicious model updates. This guards against poisoning attempts from compromised or malicious nodes.
-* **Model checkpointing:** Global model state is checkpointed round wise. Training can be paused, audited, or resumed without loss of progress.
-* **Dashboard and monitoring APIs:** A dedicated API layer exposes node status, training round progress, accuracy/loss history, privacy budget consumption, and system logs. This powers a central dashboard for the federation.
-* **Multi-label disease classification:** The global model currently classifies Pulmonary Fibrosis, Scoliosis, and Emphysema. The framework is designed to extend to additional disease labels and nodes via config.
-  </br>
+- **Proof Passport & Identity:** Creates a unique Proof Passport linked to a verified creator identity and RSA-2048 keypair, allowing every registered work to be securely associated with its creator.
 
-</div>
+- **Cryptographic Proof & Timestamping:** Generates SHA-256 fingerprints and RSA signatures for uploaded files and adds RFC 3161 timestamps to establish the integrity and existence of the exact digital work.
+
+- **Legal Evidence Generation:** Produces structured evidence and certificates aligned with the BSA 2023 Section 63 workflow, along with litigation-ready evidence packets and creator attestations.
+
+- **Invisible Watermarking & Similarity Detection:** Uses DWT-DCT invisible watermarking and perceptual hashing to help identify protected content even when copies are resized, compressed, or modified.
+
+- **Blockchain Anchoring & Audit Trail:** Anchors cryptographic proofs to the Bitcoin blockchain and maintains a traceable record of timestamps, verification events, and proof-chain information.
+
+- **Content Monitoring & Enforcement:** Detects potential unauthorized copies of registered content and assists creators by compiling infringement evidence and generating takedown packages for review.
+
+- **Multi-Format Protection:** Supports a wide range of creative work including images, illustrations, documents, scripts, audio, video, and other digital content.
+</br>
+
+<h2 align="center">
 
 <div align="center">
-  <img src="./fl_architecture.png" alt="FL_Powered_Medical_AI Architecture Diagram" width="60%">
-  <br><br>
-  <b>Architecture Overview</b>
-<br>
-End to end flow showing hospital nodes (Flower clients) training locally on their own data partitions, sending model updates to the central aggregator server for FedAvg aggregation, Byzantine detection, accuracy logging, and privacy tracking, with the resulting global model state surfaced through a React dashboard interface showing accuracy curves, privacy budget gauge, node status, round progress, and live logs.
+  <img src="image.png" alt="ProofStamp Architecture Diagram" width="60%">
 </div>
+
+<br><br>
+
+<b>Architecture Overview</b>
+
+<br>
+
+ProofStamp follows a modular microservice architecture where the React + Vite client provides the user interface and communicates with the Node.js + Express API layer. The API manages authentication, proof registration, verification workflows, database operations, and communication with external services. PostgreSQL stores users, assets, proof records, and verification data through Prisma, while the Python FastAPI steganography service handles computationally intensive operations such as image watermarking and forensic processing. Docker isolates the services and provides a consistent deployment environment. During registration, an uploaded file moves through hashing, identity signing, timestamping, optional watermarking, and proof-chain generation before the resulting evidence is stored and presented to the creator through the frontend.
+
+</div>