RSS

David Atanasov

Karma: 9

Im­mu­niza­tion against harm­ful fine-tun­ing attacks

6 Jun 2024 15:17 UTC
4 points
0 comments12 min readLW link

Train­ing-time do­main au­tho­riza­tion could be helpful for safety

25 May 2024 15:10 UTC
15 points
4 comments7 min readLW link