pith. sign in

Previous works (Maini et al., 2024; Dubi´nski et al., 2025) aggregate signal from many MIAs to yield a stronger attack

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Privacy Attacks on Image AutoRegressive Models

cs.CV · 2025-02-04 · unverdicted · novelty 7.0

Image autoregressive models leak substantially more training data than diffusion models under membership inference, dataset inference with as few as 4 samples, and data extraction attacks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Privacy Attacks on Image AutoRegressive Models cs.CV · 2025-02-04 · unverdicted · none · ref 9

    Image autoregressive models leak substantially more training data than diffusion models under membership inference, dataset inference with as few as 4 samples, and data extraction attacks.