paper-with-me

홈 › Papers

An Analysis of Untargeted Poisoning Attack and Defense Methods for Federated Online Learning to Rank Systems

2023-07-04 · Shuyi Wang, Guido Zuccon

Federated online learning to rank (FOLTR) aims to preserve user privacy by not sharing their searchable data and search interactions, while guaranteeing high search effectiveness, especially in contexts where individual users have scarce training data and interactions. For this, FOLTR trains learning to rank models in an online manner -- i.e. by exploiting users' interactions with the search systems (queries, clicks), rather than labels -- and federatively -- i.e. by not aggregating interaction data in a central server for training purposes, but by training instances of a model on each user device on their own private data, and then sharing the model updates, not the data, across a set of users that have formed the federation. Existing FOLTR methods build upon advances in federated learning. While federated learning methods have been shown effective at training machine learning models in a distributed way without the need of data sharing, they can be susceptible to attacks that target either the system's security or its overall effectiveness. In this paper, we consider attacks on FOLTR systems that aim to compromise their search effectiveness. Within this scope, we experiment with and analyse data and model poisoning attack methods to showcase their impact on FOLTR search effectiveness. We also explore the effectiveness of defense methods designed to counteract attacks on FOLTR systems. We contribute an understanding of the effect of attack and defense methods for FOLTR systems, as well as identifying the key factors influencing their effectiveness.

📄 PDF Abstract BibTeX arXiv:2307.01565

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningLearning-To-RankModel Poisoning

Similar Papers 제목 키워드 기반

Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning

2021-08-23 · Virat Shejwalkar, Amir Houmansadr, Peter Kairouz, Daniel Ramage

While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not fully understood. In this work, we aim to de…

Federated LearningMisconceptionsModel Poisoning

Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense

2022-12-11 · Yang Yu, Qi Liu, Likang Wu, Runlong Yu 외

Federated recommendation (FedRec) can train personalized recommenders without collecting user data, but the decentralized nature makes it susceptible to poisoning attacks. Most previous studies focus on the targeted atta…

Contrastive LearningRecommendation Systems

FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning

2023-12-07 · Hossein Fereidooni, Alessandro Pegoraro, Phillip Rieger, Alexandra Dmitrienko 외

Federated learning (FL) is a collaborative learning paradigm allowing multiple clients to jointly train a model without sharing their training data. However, FL is susceptible to poisoning attacks, in which the adversary…

Federated Learningimage-classificationImage ClassificationIntrusion Detection+2

Poisoning Attacks on Federated Learning for Autonomous Driving

2024-05-02 · Sonakshi Garg, Hugo Jönsson, Gustav Kalander, Axel Nilsson 외

Federated Learning (FL) is a decentralized learning paradigm, enabling parties to collaboratively train models while keeping their data confidential. Within autonomous driving, it brings the potential of reducing data st…

Autonomous DrivingFederated LearningTrajectory Prediction

On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach

2022-09-28 · Marco Anisetti, Claudio A. Ardagna, Alessandro Balestrucci, Nicola Bena 외

Machine learning is becoming ubiquitous. From finance to medicine, machine learning models are boosting decision-making processes and even outperforming humans in some tasks. This huge progress in terms of prediction qua…

Data PoisoningDecision Making