2 papers
cs.LG2025
LLMs for Analog Circuit Design Continuum (ACDC)
Yasaman Esfandiari, Jocelyn Rego, Austin Meyer +2
Large Language Models (LLMs) and transformer architectures have shown impressive reasoning and generation capabilities across diverse natural language tasks. However, their reliabi…
cs.CR2025
Provably effective detection of effective data poisoning attacks
Jonathan Gallagher, Yasaman Esfandiari, Callen MacPhee +1
This paper establishes a mathematically precise definition of dataset poisoning attack and proves that the very act of effectively poisoning a dataset ensures that the attack can b…