DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models

• URL: http://arxiv.org/abs/2410.16672v1
• Date: Tue, 22 Oct 2024 04:08:27 GMT
• Title: DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models
• Authors: Chen Qian, Dongrui Liu, Jie Zhang, Yong Liu, Jing Shao,
• Abstract summary: We introduce a training-free method to textbfDEActivate the fairness and privacy coupled textbfNeurons (textbfDEAN), which theoretically and empirically decrease the mutual information between fairness and privacy awareness. Extensive experimental results demonstrate that DEAN eliminates the trade-off phenomenon and significantly improves LLMs' fairness and privacy awareness simultaneously.
• Score: 34.73299042341535
• License:
• Abstract: Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical. Interestingly, we discover a counter-intuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT) methods significantly decreases its fairness awareness with thousands of samples. To address this issue, inspired by the information theory, we introduce a training-free method to \textbf{DEA}ctivate the fairness and privacy coupled \textbf{N}eurons (\textbf{DEAN}), which theoretically and empirically decrease the mutual information between fairness and privacy awareness. Extensive experimental results demonstrate that DEAN eliminates the trade-off phenomenon and significantly improves LLMs' fairness and privacy awareness simultaneously, \eg improving Qwen-2-7B-Instruct's fairness awareness by 12.2\% and privacy awareness by 14.0\%. More crucially, DEAN remains robust and effective with limited annotated data or even when only malicious fine-tuning data is available, whereas SFT methods may fail to perform properly in such scenarios. We hope this study provides valuable insights into concurrently addressing fairness and privacy concerns in LLMs and can be integrated into comprehensive frameworks to develop more ethical and responsible AI systems. Our code is available at \url{https://github.com/ChnQ/DEAN}.

Related papers

• A Multivocal Literature Review on Privacy and Fairness in Federated Learning [1.6124402884077915]
  Federated learning presents a way to revolutionize AI applications by eliminating the necessity for data sharing. Recent research has demonstrated an inherent tension between privacy and fairness. We argue that the relationship between privacy and fairness has been neglected, posing a critical risk for real-world applications.
  arXiv  Detail & Related papers  (2024-08-16T11:15:52Z)
• PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning [2.8304839563562436]
  Training and deploying Machine Learning models that simultaneously adhere to principles of fairness and privacy poses a significant challenge. We introduce PUFFLE, a high-level parameterised approach that can help in the exploration of the balance between utility, privacy, and fairness in FL scenarios. We prove that PUFFLE can be effective across diverse datasets, models, and data distributions, reducing the model unfairness up to 75%, with a maximum reduction in the utility of 17% in the worst-case scenario.
  arXiv  Detail & Related papers  (2024-07-21T17:22:18Z)
• No Free Lunch Theorem for Privacy-Preserving LLM Inference [30.554456047738295]
  This study develops a framework for inferring privacy-protected Large Language Models (LLMs) It lays down a solid theoretical basis for examining the interplay between privacy preservation and utility.
  arXiv  Detail & Related papers  (2024-05-31T08:22:53Z)
• TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data [50.797729676285876]
  We propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously. We theoretically quantify the privacy guarantee through the lens of the emerging f-differential privacy (DP) and the Byzantine resilience of the proposed algorithm.
  arXiv  Detail & Related papers  (2024-02-16T16:41:14Z)
• Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification [51.04894019092156]
  Federated learning (FL) has been recognized as a rapidly growing area, where the model is trained over clients under the FL orchestration (PS) In this paper, we propose a novel primal sparification algorithm for and guarantee non-smooth FL problems. Its unique insightful properties and its analyses are also presented.
  arXiv  Detail & Related papers  (2023-10-30T14:15:47Z)
• 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)
• Unraveling Privacy Risks of Individual Fairness in Graph Neural Networks [66.0143583366533]
  Graph neural networks (GNNs) have gained significant attraction due to their expansive real-world applications. To build trustworthy GNNs, two aspects - fairness and privacy - have emerged as critical considerations. Previous studies have separately examined the fairness and privacy aspects of GNNs, revealing their trade-off with GNN performance. Yet, the interplay between these two aspects remains unexplored.
  arXiv  Detail & Related papers  (2023-01-30T14:52:23Z)
• Privacy-Preserving Distributed Expectation Maximization for Gaussian Mixture Model using Subspace Perturbation [4.2698418800007865]
  federated learning is motivated by the privacy concern as it does not allow to transmit private data but only intermediate updates. We propose a fully decentralized privacy-preserving solution, which is able to securely compute the updates in each step. Numerical validation shows that the proposed approach has superior performance compared to the existing approach in terms of both the accuracy and privacy level.
  arXiv  Detail & Related papers  (2022-09-16T09:58:03Z)
• Differentially private cross-silo federated learning [16.38610531397378]
  Strict privacy is of paramount importance in distributed machine learning. In this paper we combine additively homomorphic secure summation protocols with differential privacy in the so-called cross-silo federated learning setting. We demonstrate that our proposed solutions give prediction accuracy that is comparable to the non-distributed setting.
  arXiv  Detail & Related papers  (2020-07-10T18:15:10Z)
• Provably Efficient Causal Reinforcement Learning with Confounded Observational Data [135.64775986546505]
  We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting. We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
  arXiv  Detail & Related papers  (2020-06-22T14:49:33Z)

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.