activity
20192023
most citedCertified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing

34 citations · 88 across the 17 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.CR2021★ 10 cited

Poisoning Attacks to Local Differential Privacy Protocols for Key-Value Data

Yongji Wu, Xiaoyu Cao, Jinyuan Jia +1

Local Differential Privacy (LDP) protocols enable an untrusted server to perform privacy-preserving, federated data analytics. Various LDP protocols have been developed for differe…

cs.CR2021★ 1 cited

10 Security and Privacy Problems in Large Foundation Models

Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong

Foundation models--such as GPT, CLIP, and DINO--have achieved revolutionary progress in the past several years and are commonly believed to be a promising approach for general-purp…

cs.CR2021★ 3 cited

EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning

Hongbin Liu, Jinyuan Jia, Wenjie Qu +1

Given a set of unlabeled images or (image, text) pairs, contrastive learning aims to pre-train an image encoder that can be used as a feature extractor for many downstream tasks. I…

cs.CR2021★ 16 cited

BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

Jinyuan Jia, Yupei Liu, Neil Zhenqiang Gong

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can th…

cs.CR2021

PointGuard: Provably Robust 3D Point Cloud Classification

Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

3D point cloud classification has many safety-critical applications such as autonomous driving and robotic grasping. However, several studies showed that it is vulnerable to advers…

cs.CR2021

Provably Secure Federated Learning against Malicious Clients

Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

Federated learning enables clients to collaboratively learn a shared global model without sharing their local training data with a cloud server. However, malicious clients can corr…