AI RESEARCH
Targeted Downstream-Agnostic Attack
arXiv CS.AI
•
ArXi:2605.19446v1 Announce Type: cross Recently, pre-trained encoders have gained widespread use due to their strong capability in representation extraction. However, they are vulnerable to downstream-agnostic attacks (DAAs). Existing DAA methods operate under a permissive threat model, where an attack is successful if the generated downstream-agnostic adversarial examples (DAEs) change the original prediction, without requiring a specific target.