Provable Robustness for Streaming Models with a Sliding Window
- URL: http://arxiv.org/abs/2303.16308v1
- Date: Tue, 28 Mar 2023 21:02:35 GMT
- Title: Provable Robustness for Streaming Models with a Sliding Window
- Authors: Aounon Kumar, Vinu Sankar Sadasivan and Soheil Feizi
- Abstract summary: In deep learning applications such as online content recommendation and stock market analysis, models use historical data to make predictions.
We derive robustness certificates for models that use a fixed-size sliding window over the input stream.
Our guarantees hold for the average model performance across the entire stream and are independent of stream size, making them suitable for large data streams.
- Score: 51.85182389861261
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The literature on provable robustness in machine learning has primarily
focused on static prediction problems, such as image classification, in which
input samples are assumed to be independent and model performance is measured
as an expectation over the input distribution. Robustness certificates are
derived for individual input instances with the assumption that the model is
evaluated on each instance separately. However, in many deep learning
applications such as online content recommendation and stock market analysis,
models use historical data to make predictions. Robustness certificates based
on the assumption of independent input samples are not directly applicable in
such scenarios. In this work, we focus on the provable robustness of machine
learning models in the context of data streams, where inputs are presented as a
sequence of potentially correlated items. We derive robustness certificates for
models that use a fixed-size sliding window over the input stream. Our
guarantees hold for the average model performance across the entire stream and
are independent of stream size, making them suitable for large data streams. We
perform experiments on speech detection and human activity recognition tasks
and show that our certificates can produce meaningful performance guarantees
against adversarial perturbations.
Related papers
- Importance of Disjoint Sampling in Conventional and Transformer Models for Hyperspectral Image Classification [2.1223532600703385]
This paper presents an innovative disjoint sampling approach for training SOTA models on Hyperspectral image classification (HSIC) tasks.
By separating training, validation, and test data without overlap, the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was not exposed to during training or validation.
This rigorous methodology is critical for advancing SOTA models and their real-world application to large-scale land mapping with Hyperspectral sensors.
arXiv Detail & Related papers (2024-04-23T11:40:52Z) - PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis [2.5347892611213614]
Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions.
We develop a practical method for this characteristic of model prediction and feature attribution to detect adversarial samples.
Our approach demonstrates competitive performance even when an adversary is aware of the defense mechanism.
arXiv Detail & Related papers (2024-04-12T21:22:21Z) - Quantifying Representation Reliability in Self-Supervised Learning Models [12.485580780944083]
Self-supervised learning models extract general-purpose representations from data.
We introduce a formal definition of representation reliability.
We propose an ensemble-based method for estimating the representation reliability without knowing the downstream tasks a priori.
arXiv Detail & Related papers (2023-05-31T21:57:33Z) - Preserving Knowledge Invariance: Rethinking Robustness Evaluation of
Open Information Extraction [50.62245481416744]
We present the first benchmark that simulates the evaluation of open information extraction models in the real world.
We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique.
By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
arXiv Detail & Related papers (2023-05-23T12:05:09Z) - A monitoring framework for deployed machine learning models with supply
chain examples [2.904613270228912]
We describe a framework for monitoring machine learning models; and, (2) its implementation for a big data supply chain application.
We use our implementation to study drift in model features, predictions, and performance on three real data sets.
arXiv Detail & Related papers (2022-11-11T14:31:38Z) - Robust Transferable Feature Extractors: Learning to Defend Pre-Trained
Networks Against White Box Adversaries [69.53730499849023]
We show that adversarial examples can be successfully transferred to another independently trained model to induce prediction errors.
We propose a deep learning-based pre-processing mechanism, which we refer to as a robust transferable feature extractor (RTFE)
arXiv Detail & Related papers (2022-09-14T21:09:34Z) - Uncertainty in Contrastive Learning: On the Predictability of Downstream
Performance [7.411571833582691]
We study whether the uncertainty of such a representation can be quantified for a single datapoint in a meaningful way.
We show that this goal can be achieved by directly estimating the distribution of the training data in the embedding space.
arXiv Detail & Related papers (2022-07-19T15:44:59Z) - Certifying Model Accuracy under Distribution Shifts [151.67113334248464]
We present provable robustness guarantees on the accuracy of a model under bounded Wasserstein shifts of the data distribution.
We show that a simple procedure that randomizes the input of the model within a transformation space is provably robust to distributional shifts under the transformation.
arXiv Detail & Related papers (2022-01-28T22:03:50Z) - Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions.
In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data.
We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
arXiv Detail & Related papers (2022-01-11T23:01:12Z) - Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples.
We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries.
We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
arXiv Detail & Related papers (2020-02-27T10:22:17Z)
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.