paraacha @talhaparacha.com · Dec 16

We train RNNs (small and medium sized) and GPTs (fine-tuned and trained-from-scratch) since it is unclear which approach is better for testing, in contrast to just learning (also highlighted by Godefroid et al. in Learn&Fuzz, see the snippet below for a short discussion). 4/n

0 likes 1 replies

?

Replies

paraacha · Dec 16

We find that (a) our language models trigger significant number of unique discrepancies (26 out of a maximum possible of 30) -- a discrepancy is when a TLS library accepts a certificate, while others reject it, indicating a potential bug 5/n