333 citations · 395 across the 31 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
cs.CR2024
CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
Rui Zeng, Xi Chen, Yuwen Pu +3
Backdoors can be injected into NLP models to induce misbehavior when the input text contains a specific feature, known as a trigger, which the attacker secretly selects. Unlike fix…
cs.LG2024★ 2 cited
LABOR-LLM: Language-Based Occupational Representations with Large Language Models
Susan Athey, Herman Brunborg, Tianyu Du +2
This paper builds an empirical model that predicts a worker's next occupation as a function of the worker's occupational history. Because histories are sequences of occupations, th…
cs.CR2024
An Inversion-based Measure of Memorization for Diffusion Models
Zhe Ma, Qingming Li, Xuhong Zhang +5
The past few years have witnessed substantial advances in image generation powered by diffusion models. However, it was shown that diffusion models are susceptible to training data…