#natural language process...
Aug 2026
Model Confidence Under Answer-Preserving Attacks: An Informativeness-Manipulability Frontier
This work studies model-internal confidence readouts under white-box, image-only attacks constrained to preserve the generated answer byte-identically, showing that comparable confidence movement can be induced at the representation level rather than only through adversarial images.
Reza Khanmohammadi, Ivan Brugere, Simerjot Kaur et al.
· arXiv.org · 0 citations