A Federated Learning Approach to Privacy Preserving Offensive Language Identification

• URL: http://arxiv.org/abs/2404.11470v1
• Date: Wed, 17 Apr 2024 15:23:12 GMT
• Title: A Federated Learning Approach to Privacy Preserving Offensive Language Identification
• Authors: Marcos Zampieri, Damith Premasiri, Tharindu Ranasinghe,
• Abstract summary: We propose a privacy preserving architecture for identifying offensive language online by introducing Federated Learning (FL) FL is a decentralized architecture that allows multiple models to be trained locally without the need for data sharing. We trained multiple deep learning models on four publicly available English benchmark datasets.
• Score: 14.487531876937247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The spread of various forms of offensive speech online is an important concern in social media. While platforms have been investing heavily in ways of coping with this problem, the question of privacy remains largely unaddressed. Models trained to detect offensive language on social media are trained and/or fine-tuned using large amounts of data often stored in centralized servers. Since most social media data originates from end users, we propose a privacy preserving decentralized architecture for identifying offensive language online by introducing Federated Learning (FL) in the context of offensive language identification. FL is a decentralized architecture that allows multiple models to be trained locally without the need for data sharing hence preserving users' privacy. We propose a model fusion approach to perform FL. We trained multiple deep learning models on four publicly available English benchmark datasets (AHSD, HASOC, HateXplain, OLID) and evaluated their performance in detail. We also present initial cross-lingual experiments in English and Spanish. We show that the proposed model fusion approach outperforms baselines in all the datasets while preserving privacy.

Related papers

• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• FLTrojan: Privacy Leakage Attacks against Federated Language Models Through Selective Weight Tampering [2.2194815687410627]
  We show how a malicious client can leak the privacy-sensitive data of some other users in FL even without any cooperation from the server. Our best-performing method improves the membership inference recall by 29% and achieves up to 71% private data reconstruction.
  arXiv  Detail & Related papers  (2023-10-24T19:50:01Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• Can Public Large Language Models Help Private Cross-device Federated Learning? [58.05449579773249]
  We study (differentially) private federated learning (FL) of language models. Public data has been used to improve privacy-utility trade-offs for both large and small language models. We propose a novel distribution matching algorithm with theoretical grounding to sample public data close to private data distribution.
  arXiv  Detail & Related papers  (2023-05-20T07:55:58Z)
• FedBot: Enhancing Privacy in Chatbots with Federated Learning [0.0]
  Federated Learning (FL) aims to protect data privacy through distributed learning methods that keep the data in its location. The POC combines Deep Bidirectional Transformer models and federated learning algorithms to protect customer data privacy during collaborative model training. The system is specifically designed to improve its performance and accuracy over time by leveraging its ability to learn from previous interactions.
  arXiv  Detail & Related papers  (2023-04-04T23:13:52Z)
• Federated Nearest Neighbor Machine Translation [66.8765098651988]
  In this paper, we propose a novel federated nearest neighbor (FedNN) machine translation framework. FedNN leverages one-round memorization-based interaction to share knowledge across different clients. Experiments show that FedNN significantly reduces computational and communication costs compared with FedAvg.
  arXiv  Detail & Related papers  (2023-02-23T18:04:07Z)
• Differentially Private Language Models for Secure Data Sharing [19.918137395199224]
  In this paper, we show how to train a generative language model in a differentially private manner and consequently sampling data from it. Using natural language prompts and a new prompt-mismatch loss, we are able to create highly accurate and fluent textual datasets. We perform thorough experiments indicating that our synthetic datasets do not leak information from our original data and are of high language quality.
  arXiv  Detail & Related papers  (2022-10-25T11:12:56Z)
• Selective Differential Privacy for Language Modeling [36.64464956102432]
  Previous work has attempted to tackle this challenge by training RNN-based language models with differential privacy guarantees. We propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data. Experiments on both language modeling and dialog system building show that the proposed privacy-preserving mechanism achieves better utilities.
  arXiv  Detail & Related papers  (2021-08-30T01:11:10Z)
• Evaluation of Deep Learning Models for Hostility Detection in Hindi Text [2.572404739180802]
  We present approaches for hostile text detection in the Hindi language. The proposed approaches are evaluated on the Constraint@AAAI 2021 Hindi hostility detection dataset. We evaluate a host of deep learning approaches based on CNN, LSTM, and BERT for this multi-label classification problem.
  arXiv  Detail & Related papers  (2021-01-11T19:10:57Z)
• WAFFLe: Weight Anonymized Factorization for Federated Learning [88.44939168851721]
  In domains where data are sensitive or private, there is great value in methods that can learn in a distributed manner without the data ever leaving the local devices. We propose Weight Anonymized Factorization for Federated Learning (WAFFLe), an approach that combines the Indian Buffet Process with a shared dictionary of weight factors for neural networks.
  arXiv  Detail & Related papers  (2020-08-13T04:26:31Z)
• FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition [76.26472513160425]
  We study how to make use of decentralized datasets for training a robust scene text recognizer. To make FedOCR fairly suitable to be deployed on end devices, we make two improvements including using lightweight models and hashing techniques.
  arXiv  Detail & Related papers  (2020-07-22T14:30:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.