Running
CoP Agentic Red-teaming
🧠
Generate jailbreak prompts for LLMs using human-defined principles
AI & ML interests
Research Demos and Tools for Trustworthy and Safe AI Development and Deployment
Recent Activity
View all activity
Running
AudioDeepfakeDetector
👀
Detect fake audio clips
Running
AudioPerturber
🌍
Evaluate audio deepfake detection robustness
Running
Retention Score
🧠
Evaluate jailbreak risks for Vision-Language Models
Running
1
Token Highlighter
🖍
Demonstration of Token Highlighter: A Jailbreak Defense
Running
11
GradientCuff-Jailbreak-Defense
🛡
Demonstration of Gradient Cuff: A Jailbreak Defense
Running
3
Attention Tracker Prompt Injection Detector
⚡
Attention Tracker: Prompt Injection Detector
Running
LLM Physical Safety
👀
LLM benchmark for Physical Safety
Running
NeuralFuse
⚡
Protect Model from Suffering Low-voltage-induced Bit Errors
Running
3
NCTV: Neural Clamping Toolkit and Visualization
🦀
Model-agnostic Toolkit for Neural Network Calibration
Running
1
GREAT Score
🧠
Evaluate adversarial robustness using generative models
Running
2
Defensive Prompt Patch Jailbreak Defense
🧠
Generate safe responses from language models
Running
33
RADAR AI Text Detector
📡
Identify AI-generated text