相关论文: An Equivalence Between Data Poisoning and Byzantin…
We consider a distributed reinforcement learning setting where multiple agents separately explore the environment and communicate their experiences through a central server. However, $\alpha$-fraction of agents are adversarial and can…
Multi-task learning is an effective way to address the challenge of model personalization caused by high data heterogeneity in federated learning. However, extending multi-task learning to the online decentralized federated learning setting…
As one kind of distributed machine learning technique, federated learning enables multiple clients to build a model across decentralized data collaboratively without explicitly aggregating the data. Due to its ability to break data silos,…
Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…
Despite achieving good performance and wide adoption, machine learning based security detection models (e.g., malware classifiers) are subject to concept drift and evasive evolution of attackers, which renders up-to-date threat data as a…
Network traffic prediction plays a crucial role in intelligent network operation. Traditional prediction methods often rely on centralized training, necessitating the transfer of vast amounts of traffic data to a central server. This…
The decentralized nature of federated learning, that often leverages the power of edge devices, makes it vulnerable to attacks against privacy and security. The privacy risk for a peer is that the model update she computes on her private…
Privacy-preserving federated learning allows multiple users to jointly train a model with coordination of a central server. The server only learns the final aggregation result, thus the users' (private) training data is not leaked from the…
Learned indexes are a class of index data structures that enable fast search by approximating the cumulative distribution function (CDF) using machine learning models (Kraska et al., SIGMOD'18). However, recent studies have shown that…
We study distributed stochastic gradient descent (SGD) in the master-worker architecture under Byzantine attacks. We consider the heterogeneous data model, where different workers may have different local datasets, and we do not make any…
Machine learning has begun to play a central role in many applications. A multitude of these applications typically also involve datasets that are distributed across multiple computing devices/machines due to either design constraints…
Poisoning attacks, in which an attacker adversarially manipulates the training dataset of a machine learning (ML) model, pose a significant threat to ML security. Beta Poisoning is a recently proposed poisoning attack that disrupts model…
Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on a Euclidean space;…
Decentralized federated learning (DFL) is inherently vulnerable to data poisoning attacks, as malicious clients can transmit manipulated gradients to neighboring clients. Existing defense methods either reject suspicious gradients per…
Federated Learning (FL) is a machine learning (ML) approach that enables multiple decentralized devices or edge servers to collaboratively train a shared model without exchanging raw data. During the training and sharing of model updates…
Distributed learning has become a promising computational parallelism paradigm that enables a wide scope of intelligent applications from the Internet of Things (IoT) to autonomous driving and the healthcare industry. This paper studies…
Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset. So far, it has been studied mostly for classification, even though regression…
While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisoning attacks, but these studies placed stricter requirements…
This paper investigates the robustness of over-the-air federated learning to Byzantine attacks. The simple averaging of the model updates via over-the-air computation makes the learning task vulnerable to random or intended modifications of…
Generally, regularization-based continual learning models limit access to the previous task data to imitate the real-world constraints related to memory and privacy. However, this introduces a problem in these models by not being able to…