arXiv research

New method trims network data to resist adversarial contamination.

Paper shows MoM is optimal under adversarial contamination for certain distributions.

New algorithm resists contamination in high-dimensional regression with optimal performance.

New algorithms improve robust estimation in contaminated Gaussian models.

Motivated by applications of bandit algorithms in education, we consider a stochastic multi-armed bandit problem with $\varepsilon$-contaminated rewards. We allow an adversary to give arbitrary unbounded contaminated rewards with full knowledge of the past and future. We impose the constraint that for each time $t$ the…

Algorithm identifies Pareto set in bandits with contaminated feedback.

Improved robust regression for heavy-tailed and contaminated data.

New proof shows faster convergence rate for robust estimation with Lasso in adversarially contaminated outputs.

Unified framework improves neural network robustness against label noise and adversarial attacks.

Study minimax robustness in statistical estimation under Wasserstein contamination.

Given a pair of graphs $G_1$ and $G_2$ and a vertex set of interest in $G_1$, the vertex nomination (VN) problem seeks to find the corresponding vertices of interest in $G_2$ (if they exist) and produce a rank list of the vertices in $G_2$, with the corresponding vertices of interest in $G_2$ concentrating, ideally, at…

Paper introduces MoM-KDE for robust density estimation robust to anomalous data.

The paper tackles best arm identification in contaminated bandits with optimal error guarantees and sample complexity.

Proposes new loss functions for GANs to improve estimation accuracy and robustness.

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount…

Paper introduces RAS for robust MTL with contamination.

Paper uses DNN-based MoM-GAN to estimate contaminated data distributions.

Generative models can still learn from contaminated data, but with limitations.

Paper proposes robust estimators for GANs under Wasserstein contamination.

New algorithms robust to adversarial data achieve optimal performance.

We consider the non-parametric regression problem under Huber's $ε$-contamination model, in which an $ε$ fraction of observations are subject to arbitrary adversarial noise. We first show that a simple local binning median step can effectively remove the adversary noise and this median estimator is minimax optimal up t…

The paper analyzes how conformal prediction works with contaminated reference data.

New algorithm reduces contamination in supervised learning.

FCI method uses flow-based techniques to improve prediction confidence.

Efficiently estimates mean in contaminated Gaussian data with near-optimal sample complexity.

New algorithms achieve optimal robustness in stochastic convex optimization under contamination.

Robustly estimates linear regression coefficients with adversarial and noisy data.

Study minimax rates for density estimation under Huber contamination and Besov IPM losses.

Heavy-tailed outliers are more resilient to robust estimation than adversarial ones.

Study on estimating Gaussian mean with missing data in high dimensions.

New algorithm resists corruption in linear contextual bandits.

Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which leverages clean and adversarial samples to optimize the initialization of a lear…

Study improves robustness and sparsity in linear regression with adversarial outliers and heavy-tailed noise.

New algorithm optimizes robust estimation under mixed local and global corruptions.

The paper develops adaptive confidence intervals for Efron's Gaussian two-groups model with unknown contamination.

Stochastic gradient descent on l1 loss converges to true parameter in online robust regression.

Unified approach for robust low rank matrix estimation with adversaries.

New model detects anomalies robustly in noisy, seasonal multivariate time series.

In this paper, we study the adversarial robustness of subspace learning problems. Different from the assumptions made in existing work on robust subspace learning where data samples are contaminated by gross sparse outliers or small dense noises, we consider a more powerful adversary who can first observe the data matr…

Mode estimation is a classical problem in statistics with a wide range of applications in machine learning. Despite this, there is little understanding in its robustness properties under possibly adversarial data contamination. In this paper, we give precise robustness guarantees as well as privacy guarantees under sim…

Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade classification. In this paper, we investigate the feasibility of applying a specific class of…

A contamination in a 3-manifold is an object interpolating between the contact structure and the lamination. Contaminations seem to provide a link between 3-dimensional contact geometry and the classical topology of 3-manifolds, as described in a separate paper. In this paper we deal with contaminations carried by bran…

A robust loss for anomaly mitigation and unsupervised contamination classification

New method estimates discrete distributions while protecting privacy.

Along with the advent of deep neural networks came various methods of exploitation, such as fooling the classifier or contaminating its training data. Another such attack is known as model extraction, where provided API access to some black box neural network, the adversary extracts the underlying model. This is done b…

Study shows robust method for estimating density ratios even with heavy contamination.

Paper presents robust confidence sequences for means with known moment bounds and arbitrary corruption.

This work analyzes how to choose regularization norms for adversarial training in high dimensions.