Benjamin Rubinstein | DeepAI

AI Chat

Featured Co-authors

Bo Li
461 publications
Jun Wang
360 publications
Ce Zhang
133 publications
Trevor Cohn
79 publications
Qian Chen
75 publications
Tim Miller
35 publications
Christos Dimitrakakis
30 publications
Xuanli He
23 publications
Linyi Li
21 publications
Xiaojun Xu
16 publications
Qiongkai Xu
12 publications

∙ 05/25/2023

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

Backdoor attacks are an insidious security threat against machine learni...

0 Xuanli He, et al. ∙

∙ 05/19/2023

Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation

Modern NLP models are often trained over large untrusted datasets, raisi...

0 Xuanli He, et al. ∙

∙ 04/01/2021

TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness

Adversarial Transferability is an intriguing property of adversarial exa...

0 Zhuolin Yang, et al. ∙

∙ 06/27/2020

Improving Interpretability of CNN Models Using Non-Negative Concept Activation Vectors

Convolutional neural network (CNN) models for computer vision are powerf...

14 Ruihan Zhang, et al. ∙

∙ 12/22/2015

On the Differential Privacy of Bayesian Inference

We study how to communicate findings of Bayesian inference to third part...

0 Zuhe Zhang, et al. ∙

∙ 06/05/2013

Bayesian Differential Privacy through Posterior Sampling

Differential privacy formalises privacy-preserving mechanisms that provi...

0 Christos Dimitrakakis, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world