Showing 2026Show all
3 papers · 1 filter
cs.IT2026
Limitations on Autoregressive Token Generation via Sequential Sampling
Gal Arnon, Andrej Bogdanov, Paul Lou +3
We study autoregressive token generation through the notion of sequential samplers: A circuit that samples the next symbol only given the previous ones and possibly a small amount…
cs.LG2026
Statistically Undetectable Backdoors in Deep Neural Networks
Andrej Bogdanov, Alon Rosen, Neekon Vafa
We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box…
cs.CR2026
Collision Resistance of Single-Layer Neural Nets
Marco Benedetti, Andrej Bogdanov, Enrico M. Malatesta +5
We initiate the study of the algorithmic complexity of finding collisions in single-layer binary neural networks. Given a random matrix , an…