ACM AsiaCCS 2026: BIFOLD research reveals a blind spot in #software security.
📃Shape-Shifting Malicious Code in Software Backdoors via Language Models. M E Fard, F Weissberg, E Imgrund, T Eisenhofer, K Rieck.
Link: t1p.de/8ym87
Code: t1p.de/j3rwe
#Backdoors #Attacks #MLsky #AI
@rieck.mlsec.org
BIFOLD Berlin Institute for the Foundations of Learning and Data
