Unclaimed profileBuilt from public GitHub and Hugging Face activity. Pradyoth has not joined Lounge yet.Claim it
Not on Lounge yet
Pradyoth P
developerGen AI Red Team @ JPMorganChase ·
Public projects
prompt-injection-ctf
Free prompt injection CTF: 16 LLM security missions plus a 30-mission Agentic Security Lab (OWASP Agentic Top 10), defender mode, optional live-model grading. No signup.
HTMLagentic-aiai-agentsai-safety
AgentInjectionBench
Catch unsafe tool calls before you ship. Test prompt injection in tool-using agents with reproducible traces and benign controls.
Pythonagentic-aiai-safetybenchmark
ai-security-resources
A curated collection of frameworks, tools, methodologies, and papers for AI Red Teaming, LLM Security, and MLSecOps.
ai-safetyai-securityjailbreaking
stock-predictor
This project is part of the AI-ML course (Industry driven Elective by Nokia) and aims to help retail investors make an informed choice about choosing to go long/short on a particular stock. As quoted in the TV-show Billions "Everyone has the data, we analyze it better". This project delivers high quality insights from raw data.
Jupyter Notebookdata-sciencemachine-learningmlops
weighted-safety-refusal
Severity-weighted LLM safety evaluation suite. Measures absolute refusal robustness across prompt injection, jailbreaking, data exfiltration, toxicity, and malware generation — with risk-adjusted category weights and a custom model-graded scorer.
Pythonai-safetyai-securityjailbreaking
ML-101-Workshop
This repo contains src code used during the ML - 101 workshop hosted by IEEE Bangalore Section as a part of IEEE CCONNECT.
Jupyter Notebookdata-sciencemachine-learningmlops
Likely stack
ClaudeLangChainLlamaNext.jsTransformersOllamaCursorMCPDiffusion
