I am Sarbartha Banerjee, a post-doctoral fellow at The University of Texas at Austin, with Dr. Mohit Tiwari. My research centers on integrating artificial intelligence techniques with system-level defense mechanisms—spanning both software and hardware—to enhance the security and resilience of large language model (LLM) systems.
I am Sarbartha Banerjee, a post-doctoral fellow at The University of Texas at Austin, with Dr. Mohit Tiwari. My research centers on integrating artificial intelligence techniques with system-level defense mechanisms—spanning both software and hardware—to enhance the security and resilience of large language model (LLM) systems.
I am currently designing a red-teaming framework that composes traditional software and hardware attack gadgets to catalyze adversarial attacks in compound AI pipelines.
I am currently designing a red-teaming framework that composes traditional software and hardware attack gadgets to catalyze adversarial attacks in compound AI pipelines.