Search Results - seyed+hamed+hassani

2 Results Sort By:
SMOOTHLLM: Defending Large Language Models Against Jailbreaking Attacks
An algorithm designed to defend Large Language Models (LLMs) against jailbreaking attacks that significantly reduces attack success rates. Problem: Despite efforts to align LLM outputs with ethical standards, the models exhibit persistent weaknesses against adversarial attacks that bypass alignment mechanisms and safety guardrails, commonly known as...
Published: 1/28/2025   |   Inventor(s): George Pappas, Alexander Beck Robey, Seyed Hamed Hassani, Eric Wong
Keywords(s): Artificial Intelligence (AI) & Machine Learning, Software
Category(s): Technology Classifications > Business Ideas, Technology Classifications > Computer Information Systems
Versatile Algorithm For Safe And Accurate Deep Learning
Model-based robust deep learning algorithms allow for more accurate and robust predictions in varying environmental conditions. Problem: In applications that rely on safe and reliable predictions such as autonomous vehicles, medical imaging, and robotics, it is essential that the prediction systems be made robust against nuisance variability such...
Published: 10/16/2023   |   Inventor(s): George Pappas, Seyed Hamed Hassani, Alexander Beck Robey
Keywords(s): Artificial Intelligence (AI) & Machine Learning, Autonomous Vehicles
Category(s): Technology Classifications > Computer Information Systems