Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features
- URL: http://arxiv.org/abs/2405.01207v1
- Date: Thu, 2 May 2024 11:48:30 GMT
- Title: Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features
- Authors: Francisco Teixeira, Karla Pizzi, Raphael Olivier, Alberto Abad, Bhiksha Raj, Isabel Trancoso,
- Abstract summary: Membership Inference (MI) poses a substantial privacy threat to the training data of Automatic Speech Recognition (ASR) systems.
This paper explores the effectiveness of loss-based features in combination with Gaussian and adversarial perturbations to perform MI in ASR models.
- Score: 32.765965044767356
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Membership Inference (MI) poses a substantial privacy threat to the training data of Automatic Speech Recognition (ASR) systems, while also offering an opportunity to audit these models with regard to user data. This paper explores the effectiveness of loss-based features in combination with Gaussian and adversarial perturbations to perform MI in ASR models. To the best of our knowledge, this approach has not yet been investigated. We compare our proposed features with commonly used error-based features and find that the proposed features greatly enhance performance for sample-level MI. For speaker-level MI, these features improve results, though by a smaller margin, as error-based features already obtained a high performance for this task. Our findings emphasise the importance of considering different feature sets and levels of access to target models for effective MI in ASR systems, providing valuable insights for auditing such models.
Related papers
- Efficient Network Traffic Feature Sets for IoT Intrusion Detection [0.0]
This work evaluates the feature sets provided by a combination of different feature selection methods, namely Information Gain, Chi-Squared Test, Recursive Feature Elimination, Mean Absolute Deviation, and Dispersion Ratio, in multiple IoT network datasets.
The influence of the smaller feature sets on both the classification performance and the training time of ML models is compared, with the aim of increasing the computational efficiency of IoT intrusion detection.
arXiv Detail & Related papers (2024-06-12T09:51:29Z) - InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling [66.3072381478251]
Reward hacking, also termed reward overoptimization, remains a critical challenge.
We propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective.
We show that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets.
arXiv Detail & Related papers (2024-02-14T17:49:07Z) - Word-Level ASR Quality Estimation for Efficient Corpus Sampling and
Post-Editing through Analyzing Attentions of a Reference-Free Metric [5.592917884093537]
The potential of quality estimation (QE) metrics is introduced and evaluated as a novel tool to enhance explainable artificial intelligence (XAI) in ASR systems.
The capabilities of the NoRefER metric are explored in identifying word-level errors to aid post-editors in refining ASR hypotheses.
arXiv Detail & Related papers (2024-01-20T16:48:55Z) - Augmenting Unsupervised Reinforcement Learning with Self-Reference [63.68018737038331]
Humans possess the ability to draw on past experiences explicitly when learning new tasks.
We propose the Self-Reference (SR) approach, an add-on module explicitly designed to leverage historical information.
Our approach achieves state-of-the-art results in terms of Interquartile Mean (IQM) performance and Optimality Gap reduction on the Unsupervised Reinforcement Learning Benchmark.
arXiv Detail & Related papers (2023-11-16T09:07:34Z) - Generalizable Error Modeling for Search Relevance Data Annotation Tasks [0.0]
Human data annotation is critical in shaping the quality of machine learning (ML) and artificial intelligence (AI) systems.
One significant challenge in this context is posed by annotation errors, as their effects can degrade the performance of ML models.
This paper presents a predictive error model trained to detect potential errors in search relevance annotation tasks for three industry-scale ML applications.
arXiv Detail & Related papers (2023-10-08T21:21:19Z) - Understanding Self-attention Mechanism via Dynamical System Perspective [58.024376086269015]
Self-attention mechanism (SAM) is widely used in various fields of artificial intelligence.
We show that intrinsic stiffness phenomenon (SP) in the high-precision solution of ordinary differential equations (ODEs) also widely exists in high-performance neural networks (NN)
We show that the SAM is also a stiffness-aware step size adaptor that can enhance the model's representational ability to measure intrinsic SP.
arXiv Detail & Related papers (2023-08-19T08:17:41Z) - On the Efficacy of Generalization Error Prediction Scoring Functions [33.24980750651318]
Generalization error predictors (GEPs) aim to predict model performance on unseen distributions by deriving dataset-level error estimates from sample-level scores.
We rigorously study the effectiveness of popular scoring functions (confidence, local manifold smoothness, model agreement) independent of mechanism choice.
arXiv Detail & Related papers (2023-03-23T18:08:44Z) - Discover, Explanation, Improvement: An Automatic Slice Detection
Framework for Natural Language Processing [72.14557106085284]
slice detection models (SDM) automatically identify underperforming groups of datapoints.
This paper proposes a benchmark named "Discover, Explain, improve (DEIM)" for classification NLP tasks.
Our evaluation shows that Edisa can accurately select error-prone datapoints with informative semantic features.
arXiv Detail & Related papers (2022-11-08T19:00:00Z) - FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised
Learning Features in Robust End-to-end Speech Recognition [34.40924909515384]
We propose to investigate effectiveness of diverse SSLR combinations using various fusion methods within end-to-end (E2E) ASR models.
We show that the proposed 'FeaRLESS learning features' perform better than systems without the proposed feature refinement loss for both the WSJ and Fearless Steps Challenge (FSC) corpora.
arXiv Detail & Related papers (2022-06-30T06:39:40Z) - Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution
Detection [55.028065567756066]
Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications.
In this paper we propose an uncertainty quantification approach by modelling the distribution of features.
We incorporate an efficient ensemble mechanism, namely batch-ensemble, to construct the batch-ensemble neural networks (BE-SNNs) and overcome the feature collapse problem.
We show that BE-SNNs yield superior performance on several OOD benchmarks, such as the Two-Moons dataset, the FashionMNIST vs MNIST dataset, FashionM
arXiv Detail & Related papers (2022-06-26T16:00:22Z) - Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images.
Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
arXiv Detail & Related papers (2021-01-07T07:33:38Z)
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.