86 citations · 255 across the 20 of their papers we have counts for
4 papers · 1 filter
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
Zhaohan Xi, Tianyu Du, Changjiang Li +5
Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this…
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
Bochuan Cao, Yuanpu Cao, Lu Lin +1
Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs c…
Coskewness under dependence uncertainty
Carole Bernard, Jinghui Chen, Ludger Ruschendorf +1
We study the impact of dependence uncertainty on the expectation of the product of random variables, when for all~. Under some…
On the Vulnerability of Backdoor Defenses for Federated Learning
Pei Fang, Jinghui Chen
Federated Learning (FL) is a popular distributed machine learning paradigm that enables jointly training a global model without sharing clients' data. However, its repetitive serve…