Papers Model Poisoning
“Model Poisoning” 태그가 달린 논문 108편 · 필터 해제
RepuNet: A Reputation System for Mitigating Malicious Clients in DFL
Decentralized Federated Learning (DFL) enables nodes to collaboratively train models without a central server, introducing new vulnerabilities since each node independently selects peers for model aggregation. Malicious …
Federated LearningModel PoisoningFederated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Models
With the widespread application of edge computing and cloud systems in AI-driven applications, how to maintain efficient performance while ensuring data privacy has become an urgent security issue. This paper proposes a …
Edge-computingFederated LearningModel PoisoningTrojan Horse Hunt in Time Series Forecasting for Space Operations
This competition hosted on Kaggle (https://www.kaggle.com/competitions/trojan-horse-hunt-in-space) is the first part of a series of follow-up competitions and hackathons related to the "Assurance for Space Domain AI Appl…
Model PoisoningTime SeriesTime Series AnalysisTime Series ForecastingPerformance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach
Manipulation of local training data and local updates, i.e., the poisoning attack, is the main threat arising from the collaborative nature of the federated learning (FL) paradigm. Most existing poisoning attacks aim to …
Federated LearningModel PoisoningGRANITE : a Byzantine-Resilient Dynamic Gossip Learning Framework
Gossip Learning (GL) is a decentralized learning paradigm where users iteratively exchange and aggregate models with a small set of neighboring peers. Recent GL approaches rely on dynamic communication graphs built and m…
Model PoisoningA Client-level Assessment of Collaborative Backdoor Poisoning in Non-IID Federated Learning
Federated learning (FL) enables collaborative model training using decentralized private data from multiple clients. While FL has shown robustness against poisoning attacks with basic defenses, our research reveals new v…
Federated LearningModel PoisoningTwo Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Poisoning Attacks
Federated Learning is a popular paradigm that enables remote clients to jointly train a global model without sharing their raw data. However, FL has been shown to be vulnerable towards model poisoning attacks due to its …
Federated LearningModel PoisoningNot All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning
Federated Ranking Learning (FRL) is a state-of-the-art FL framework that stands out for its communication efficiency and resilience to poisoning attacks. It diverges from the traditional FL framework in two ways: 1) it l…
AllFederated LearningModel PoisoningPoisoning Bayesian Inference via Data Deletion and Replication
Research in adversarial machine learning (AML) has shown that statistical models are vulnerable to maliciously altered data. However, despite advances in Bayesian machine learning models, most AML research remains concen…
Bayesian InferenceModel PoisoningSLVR: Securely Leveraging Client Validation for Robust Federated Learning
Federated Learning (FL) enables collaborative model training while keeping client data private. However, exposing individual client updates makes FL vulnerable to reconstruction attacks. Secure aggregation mitigates such…
Federated LearningModel PoisoningDual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
Federated learning (FL) is inherently susceptible to privacy breaches and poisoning attacks. To tackle these challenges, researchers have separately devised secure aggregation mechanisms to protect data privacy and robus…
Anomaly DetectionFederated LearningModel PoisoningDMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differences
Federated learning (FL) has garnered significant attention as a prominent privacy-preserving Machine Learning (ML) paradigm. Decentralized FL (DFL) eschews traditional FL's centralized server architecture, enhancing the …
Federated LearningmodelModel PoisoningPrivacy PreservingSoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and model poisoning attacks (MPAs) that deg…
BenchmarkingData PoisoningFederated LearningModel PoisoningMaximizing Uncertainty for Federated learning via Bayesian Optimisation-based Model Poisoning
As we transition from Narrow Artificial Intelligence towards Artificial Super Intelligence, users are increasingly concerned about their privacy and the trustworthiness of machine learning (ML) technology. A common denom…
Bayesian OptimisationFederated LearningModel PoisoningPrivacy PreservingVerifBFL: Leveraging zk-SNARKs for A Verifiable Blockchained Federated Learning
Blockchain-based Federated Learning (FL) is an emerging decentralized machine learning paradigm that enables model training without relying on a central server. Although some BFL frameworks are considered privacy-preserv…
Federated LearningModel PoisoningPrivacy PreservingSNARKSTazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning
Federated learning enables decentralized model training without sharing raw data, preserving data privacy. However, its vulnerability towards critical security threats, such as gradient inversion and model poisoning by m…
Computational EfficiencyFederated LearningModel PoisoningDeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also o…
Adversarial AttackBackdoor AttackFederated LearningModel PoisoningHow to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution
Federated learning (FL) is vulnerable to model poisoning attacks due to its distributed nature. The current defenses start from all user gradients (model updates) in each communication round and solve for the optimal agg…
Federated LearningModel PoisoningFedSECA: Sign Election and Coordinate-wise Aggregation of Gradients for Byzantine Tolerant Federated Learning
One of the most common defense strategies against Byzantine clients in federated learning (FL) is to employ a robust aggregator mechanism that makes the training more resilient. While many existing Byzantine robust aggre…
Federated LearningModel PoisoningMeta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
Federated learning (FL) is susceptible to a range of security threats. Although various defense mechanisms have been proposed, they are typically non-adaptive and tailored to specific types of attacks, leaving them insuf…
Federated LearningMeta-LearningModel PoisoningReinforcement Learning (RL)