Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. However, as LLMs have improved, so have the attacks against them. Prompt injection attack is listed as the #1 threat by OWASP to LLM-integrated applications, where an LLM input contains a trusted prompt (instruction) and an untrusted data. The…

In order to produce effective targeted therapies for cancer, scientists need to isolate the genetic and phenotypic characteristics of cancer cells, both within and across different tumors, because those differences impact how tumors respond to treatment. Part of this work requires a deep understanding of the RNA or protein molecules…

When large language models like ChatGPT first became widely available, a lot of us developers felt like we’d been handed a new superpower. We could use LLMs to help us develop new coding projects, build websites, and much more – just using a few prompts. LLMs were like a tireless,…