Pith. sign in

A survey of recent backdoor attacks and defenses in large language models

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

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Towards more transferable adversarial attack in black-box manner

cs.LG · 2025-05-23 · conditional · novelty 6.0

ScorePGD and U-ScorePGD craft transferable black-box adversarial examples by optimizing the log-likelihood of a time-dependent classifier on a single noisy sample, matching or beating DiffPGD at roughly 10x lower cost.

citing papers explorer

Showing 1 of 1 citing paper.

  • Towards more transferable adversarial attack in black-box manner cs.LG · 2025-05-23 · conditional · none · ref 3

    ScorePGD and U-ScorePGD craft transferable black-box adversarial examples by optimizing the log-likelihood of a time-dependent classifier on a single noisy sample, matching or beating DiffPGD at roughly 10x lower cost.