Pytorch, Python, Cuda, LLM and foundation models

Pytorch, Cuda, Python, LLM and foundation models

Machine Learning, Unsupervised Learning, Python, Model Backdoor Detection, Data Poisoning, Red-teaming Frontier AI Systems, Adversarial Machine Learning, Adversarial Robustness, Adversarial Machine Learning AI Agent Security, ML Safety, reinforcement learning, ML Interpretability, Debugging Complex ML Failure Modes, Multi-object Optimization, Generative Models, supervised learning, Reverse Engineering Model Behaviors, Agentic AI, Evaluating Frontier AI Systems, Prompt Injection