174 citations · 313 across the 26 of their papers we have counts for
24 papers · 1 filter
Pool Inference Attacks on Local Differential Privacy: Quantifying the Privacy Guarantees of Apple's Count Mean Sketch in Practice
Andrea Gadotti, Florimond Houssiau, Meenatchi Sundaram Muthu Selva Annamalai +1
Behavioral data generated by users' devices, ranging from emoji use to pages visited, are collected at scale to improve apps and services. These data, however, contain fine-grained…
PORE: Provably Robust Recommender Systems against Data Poisoning Attacks
Jinyuan Jia, Yupei Liu, Yuepeng Hu +1
Data poisoning attacks spoof a recommender system to make arbitrary, attacker-desired recommendations via injecting fake users with carefully crafted rating scores into the recomme…
PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees
Jinghuai Zhang, Jinyuan Jia, Hongbin Liu +1
Point cloud classification is an essential component in many security-critical applications such as autonomous driving and augmented reality. However, point cloud classifiers are v…
REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service
Wenjie Qu, Jinyuan Jia, Neil Zhenqiang Gong
Encoder as a service is an emerging cloud service. Specifically, a service provider first pre-trains an encoder (i.e., a general-purpose feature extractor) via either supervised le…
Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning
Hongbin Liu, Wenjie Qu, Jinyuan Jia +1
Classifiers in supervised learning have various security and privacy issues, e.g., 1) data poisoning attacks, backdoor attacks, and adversarial examples on the security side as wel…
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
Jinghuai Zhang, Hongbin Liu, Jinyuan Jia +1
Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poison…
FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information
Xiaoyu Cao, Jinyuan Jia, Zaixi Zhang +1
Federated learning is vulnerable to poisoning attacks in which malicious clients poison the global model via sending malicious model updates to the server. Existing defenses focus…
FLCert: Provably Secure Federated Learning against Poisoning Attacks
Xiaoyu Cao, Zaixi Zhang, Jinyuan Jia +1
Due to its distributed nature, federated learning is vulnerable to poisoning attacks, in which malicious clients poison the training process via manipulating their local training d…
MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples
Jinyuan Jia, Wenjie Qu, Neil Zhenqiang Gong
Multi-label classification, which predicts a set of labels for an input, has many applications. However, multiple recent studies showed that multi-label classification is vulnerabl…
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning
Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
Contrastive learning pre-trains an image encoder using a large amount of unlabeled data such that the image encoder can be used as a general-purpose feature extractor for various d…
StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning
Yupei Liu, Jinyuan Jia, Hongbin Liu +1
Pre-trained encoders are general-purpose feature extractors that can be used for many downstream tasks. Recent progress in self-supervised learning can pre-train highly effective e…
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…
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…
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…
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…
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…
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…
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks
Jinyuan Jia, Yupei Liu, Xiaoyu Cao +1
Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via modifying, adding, and/or removing some carefully selected training examples, such that…
Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations
Jinyuan Jia, Binghui Wang, Xiaoyu Cao +2
Top-k predictions are used in many real-world applications such as machine learning as a service, recommender systems, and web searches. -norm adversarial perturbation char…
Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation
Binghui Wang, Jinyuan Jia, Xiaoyu Cao +1
Graph neural networks (GNNs) have recently gained much attention for node and graph classification tasks on graph-structured data. However, multiple recent works showed that an att…
Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks
Jinyuan Jia, Xiaoyu Cao, Neil Zhenqiang Gong
In a \emph{data poisoning attack}, an attacker modifies, deletes, and/or inserts some training examples to corrupt the learnt machine learning model. \emph{Bootstrap Aggregating (b…
Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing
Jinyuan Jia, Binghui Wang, Xiaoyu Cao +1
Community detection plays a key role in understanding graph structure. However, several recent studies showed that community detection is vulnerable to adversarial structural pertu…
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
Minghong Fang, Xiaoyu Cao, Jinyuan Jia +1
In federated learning, multiple client devices jointly learn a machine learning model: each client device maintains a local model for its local training dataset, while a master dev…
Data Poisoning Attacks to Local Differential Privacy Protocols
Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong
Local Differential Privacy (LDP) protocols enable an untrusted data collector to perform privacy-preserving data analytics. In particular, each user locally perturbs its data to pr…