Breaking Down Barriers: How LLMs Enable Software Analysis in Classified Environments
Software Engineering Institute (SEI) Podcast Series

Breaking Down Barriers: How LLMs Enable Software Analysis in Classified Environments

B2Upper-intermediateAugust 6, 202621 min
  • Interview
  • Technology

The recent explosion in large language model (LLM) technology has highlighted the challenges of using public generative artificial intelligence tools in classified environments, especially for software analysis. Currently, software analysis falls on the shoulders of static analysis tools and manual code review, which tend to provide limited technical depth and are often time-consuming in practice. In our latest podcast from the Carnegie Mellon University Software Engineering Institute (SEI), Ryan Karl, an SEI embedded engineer, and John Robert, deputy director of the SEI's Software Solutions Division, discuss their work on using LLMs in unclassified environments to rapidly develop tools that...

Play episode

Opens the player: the full transcript, every word clickable, with translation and flashcards.

Try it: tap any word

Real sentences from the start of this episode. Every word is marked with its level.

Sentence 4 of 12 · 0:14

This is because when you take software and move it into the classified space,

to make sure we're not introducing vulnerabilities into a classified environment.

Tap a word to see its meaning in your language.

Do you know these words?

8 harder words from this episode. Tap one to see what it means, then mark it.

Mark a few words and we'll tell you how this episode fits your level.

Is this episode right for you?

B2

B2 · Upper-intermediate

Comfortable if you already follow TV news

A1 29%A2 31%B1 19%B2 13%C1 7%
  • 80% of the words are B1 or easier.
  • 183 words a minute: natural, fairly fast speech.
  • 124 harder words (B2 and up) in the whole episode.

Transcript

The opening of the episode. The whole transcript is in the player.

0:00

A lot of classified environments typically have software that is a little bit behind state-of-the-art leading technologies from the private industry. This is because when you take software and move it into the classified space, it takes a long time to do the hardcore security analysis

0:17

to make sure we're not introducing vulnerabilities into a classified environment. What happens in times like today where we have AI transforming how we do our work, right? These models are evolving rapidly and they're rapidly developing new capabilities that are super important for the warfighter to utilize in their day-to-day work. What

0:38

we need to do is we need to find a way to compromise between the constraints of a classified environment so that we can yield the benefits of these leading industry technologies and move them to the classified space in a safe, secure way. The recent explosion in large language model development has accelerated many parts of the

That was the opening. The rest of the episode (21 min) is in the player: every word clickable, with translation, saved words and flashcards.

Continue in the player

Automatically generated from the audio. May contain errors. Audio belongs to its publisher and is played from their feed. Rights holders can request removal — copyright & takedown policy