Update README.md

README.md

@@ -1,73 +1,73 @@
----
-title: Multimodal Misinformation Detection
-emoji: 🔍
-colorFrom: red
-colorTo: blue
-sdk: gradio
-sdk_version: 4.0.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-# 🔍 Multimodal Misinformation Detection System
-
-**Detect AI-generated text, deepfake images, and coordinated disinformation campaigns using deep learning.**
-
-## 🚀 Features
-
-- **Text Analysis**: Identify AI-generated content from GPT, ChatGPT, and other LLMs
-- **Image Analysis**: Detect deepfake and manipulated images
-- **Real-time Processing**: Get results in under 2 seconds
-- **High Accuracy**: 93-95% detection accuracy on benchmark datasets
-
-## 🎯 Use Cases
-
-- Social media content moderation
-- News verification and fact-checking
-- Academic integrity monitoring
-- Digital forensics investigation
-
-## 🛠️ Technology
-
-- **Models**: EfficientNet-B4, RoBERTa-base, GPT-2
-- **Frameworks**: PyTorch, Transformers, Gradio
-- **Detection**: Face analysis, artifact detection, perplexity scoring
-
-## 📊 Performance
-
-| Task | Accuracy | Speed |
-|------|----------|-------|
-| Text Detection | 95% | <1s |
-| Image Detection | 93% | <2s |
-| Video Analysis | 91% | ~5s |
-
-## 💡 How It Works
-
-### Text Analysis
-1. Analyzes writing patterns and vocabulary
-2. Calculates perplexity using GPT-2
-3. Classifies as human or AI-generated
-4. Provides confidence score and explanation
-
-### Image Analysis
-1. Detects faces in the image
-2. Analyzes facial features for manipulation
-3. Identifies compression artifacts
-4. Classifies as authentic or deepfake
-
-## 🔗 Links
-
-- [GitHub Repository](https://github.com/YOUR_USERNAME/multimodal-misinformation-detection)
-- [API Documentation](https://github.com/YOUR_USERNAME/multimodal-misinformation-detection#api)
-- [Technical Paper](https://github.com/YOUR_USERNAME/multimodal-misinformation-detection/blob/main/ARCHITECTURE.md)
-
-## 👤 Author
-
-Built by **Shreyas Gosavi** for Google DeepMind Research Engineer application.
-
-Addressing the challenge of information quality and online misinformation through multimodal AI detection.
-
-## 📝 License
-
-MIT License - See LICENSE file for details
+---
+title: Multimodal Misinformation Detection
+emoji: 🔍
+colorFrom: red
+colorTo: blue
+sdk: gradio
+sdk_version: 6.5.1
+app_file: app.py
+pinned: false
+license: mit
+---
+
+# 🔍 Multimodal Misinformation Detection System
+
+**Detect AI-generated text, deepfake images, and coordinated disinformation campaigns using deep learning.**
+
+## 🚀 Features
+
+- **Text Analysis**: Identify AI-generated content from GPT, ChatGPT, and other LLMs
+- **Image Analysis**: Detect deepfake and manipulated images
+- **Real-time Processing**: Get results in under 2 seconds
+- **High Accuracy**: 93-95% detection accuracy on benchmark datasets
+
+## 🎯 Use Cases
+
+- Social media content moderation
+- News verification and fact-checking
+- Academic integrity monitoring
+- Digital forensics investigation
+
+## 🛠️ Technology
+
+- **Models**: EfficientNet-B4, RoBERTa-base, GPT-2
+- **Frameworks**: PyTorch, Transformers, Gradio
+- **Detection**: Face analysis, artifact detection, perplexity scoring
+
+## 📊 Performance
+
+| Task | Accuracy | Speed |
+|------|----------|-------|
+| Text Detection | 95% | <1s |
+| Image Detection | 93% | <2s |
+| Video Analysis | 91% | ~5s |
+
+## 💡 How It Works
+
+### Text Analysis
+1. Analyzes writing patterns and vocabulary
+2. Calculates perplexity using GPT-2
+3. Classifies as human or AI-generated
+4. Provides confidence score and explanation
+
+### Image Analysis
+1. Detects faces in the image
+2. Analyzes facial features for manipulation
+3. Identifies compression artifacts
+4. Classifies as authentic or deepfake
+
+## 🔗 Links
+
+- [GitHub Repository](https://github.com/YOUR_USERNAME/multimodal-misinformation-detection)
+- [API Documentation](https://github.com/YOUR_USERNAME/multimodal-misinformation-detection#api)
+- [Technical Paper](https://github.com/YOUR_USERNAME/multimodal-misinformation-detection/blob/main/ARCHITECTURE.md)
+
+## 👤 Author
+
+Built by **Shreyas Gosavi** for Google DeepMind Research Engineer application.
+
+Addressing the challenge of information quality and online misinformation through multimodal AI detection.
+
+## 📝 License
+
+MIT License - See LICENSE file for details