Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this paper, we propose the first quantitative analysis of the robustness of classifiers to universal perturba…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “robust perturbation analysis”
PAC-Bayesian bounds estimate adversarial robustness.
problem Estimating robustness to imperceptible input perturbations.
method PAC-Bayesian framework for averaging over hypotheses.
result General bounds valid for any type of adversarial attacks.
New research evaluates various perturbation methods for improving neural network robustness.
problem Understanding and improving robustness of Convolutional Neural Networks (CNNs) against adversarial attacks.
method Detailed evaluation of five main perturbation-based defenses, comparing random and deterministic approaches.
result Perturbation-based defenses are equivalent in efficacy, and attacks transfer between them.
Paper develops robust estimators and strategies for stochastic MABs with heavy-tailed rewards.
problem Stochastic multi-armed bandits with heavy-tailed rewards.
method Proposes a novel robust estimator and perturbation-based exploration strategy.
result Develops upper and lower regret bounds for various perturbations.
Unified analysis of removal-based feature attributions robustness.
problem Robustness of removal-based feature attributions is not well understood.
method Theoretical analysis and upper bounds derivation for removal-based feature attributions under input and model perturbations.
result Upper bounds for the difference between intact and perturbed attributions derived under various perturbation settings.
Adding node feature kernels improves GCN robustness to graph perturbations.
problem GCNs' robustness to graph perturbations is a concern.
method Introduced random GCN and added node feature kernels to message passing.
result Perturbations of the graph structure can significantly degrade GCN performance.
Our research tackles robustness to multiple perturbations in adversarial training.
problem Defenses against adversarial examples are tailored to single perturbation types and offer no guarantees for others.
method We analyze and train models robust to multiple -bounded and spatial perturbations.
result No model trained against multiple attacks achieves robustness competitive with individual training.
Generalizes robust statistics to various perturbations under Wasserstein distance.
problem Robust statistics for datasets corrupted by various perturbations.
method Generalizes robust statistics to any Wasserstein distance, showing robust estimation under certain perturbations.
result Generalized resilience property holds under moment or hypercontractive conditions, simplifying and improving known results.
Study shows image classifiers struggle with temporal changes in videos.
problem Temporal robustness of image classifiers in videos.
method Constructed datasets and evaluated various classifiers and detection models.
result Median classification accuracy drops of 16-10 points in robust datasets.
Automates perturbation analysis for neural networks, enabling certified robustness on complex architectures.
problem Limited applicability of existing perturbation analysis methods to complex neural network architectures.
method Developed an automatic framework to generalize LiRPA algorithms to any neural network structure, enabling loss fusion and state-of-the-art certified defense results.
result Demonstrated LiRPA based certified defense on Tiny ImageNet and Downscaled ImageNet.
This paper improves conformal prediction to be robust to perturbations.
problem Ensuring robustness of conformal prediction to natural and adversarial perturbations.
method Probabilistically robust conformal prediction (PRCP) and its adaptive version (aPRCP).
result aPRCP achieves better trade-offs between nominal performance and robustness.
Statistical Robustness of Interval CVaR Based Regression Models under Perturbation and Contaminationmath.OC
Study enhances robustness of In-CVaR based regression models under perturbation and contamination.
problem Enhancing robustness of nonlinear regression models under perturbation and contamination.
method Introduces interval conditional value-at-risk (In-CVaR) and rigorously analyzes its robustness properties under both perturbation and contamination.
result The In-CVaR based estimator is qualitatively robust in terms of the Prokhorov metric if and only if the largest portion of losses is trimmed.
This work improves PCA for robustness against adversarial perturbations.
problem Vulnerability of machine learning systems to small perturbations.
method Formulated and optimized a robust variant of PCA.
result Polynomial time algorithm that is competitive in worst-case robustness.
This work introduces adversarial sparsity to measure robustness beyond adversarial accuracy.
problem Evaluating robustness to adversarial attacks beyond just accuracy.
method Adversarial sparsity, which quantifies the difficulty of finding perturbations.
result Sparsity provides valuable insights into neural networks and suggests improvements in robustness.
The goal of this paper is to analyze an intriguing phenomenon recently discovered in deep networks, namely their instability to adversarial perturbations (Szegedy et. al., 2014). We provide a theoretical framework for analyzing the robustness of classifiers to adversarial perturbations, and show fundamental upper bound…
This paper improves DQN agents' robustness to adversarial perturbations.
problem Improving DQN agents' robustness to adversarial perturbations.
method Adversarial training and a novel AGE mechanism based on -greedy and Boltzmann exploration.
result AGE mechanism enhances DQN agents' robustness to adversarial perturbations.
Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the…
The paper shows how policy regularization acts like an adversary to improve robustness.
problem Improving robustness of learned policies in reinforcement learning.
method Using convex duality, the paper characterizes adversarial reward perturbations and provides generalization guarantees.
result Policy regularization acts as an adversary to improve robustness against worst-case reward perturbations.
This paper analyzes -Variational Classifiers for robustness and adversarial perturbation detection.
problem Limited robustness of deep neural networks in predictions.
method An analysis of -Variational Classifiers, focusing on their robustness and adversarial perturbation detection.
result Novel insights into the generative component of -Variational Classifiers.
State entropy regularization improves robustness in reinforcement learning, especially under structured perturbations.
problem Structured and spatially correlated perturbations in reinforcement learning.
method State entropy regularization, compared to policy entropy.
result State entropy regularization provides better robustness to structured and spatially correlated perturbations.
GNNs robustness in community detection is studied with various perturbations.
problem Understanding GNNs robustness in community detection tasks.
method Systematic computational evaluation of six GNN architectures on synthetic and real-world networks.
result Supervised GNNs achieve higher baseline accuracy, while DMoN shows stronger resilience to perturbations.
Paper introduces new evaluation criteria for feature-based model explanations.
problem Establishing reliable feature importance explanations for models.
method Robustness analysis using smaller adversarial perturbations.
result New explanations that are necessary and sufficient for predictions.
Study shows adversarial robustness and common perturbation robustness are independent.
problem Understanding the relationship between adversarial robustness and common perturbation robustness in neural networks.
method Conducted experiments to benchmark neural network robustness to common perturbations and adversarial examples.
result Adversarial robustness and common perturbation robustness are independent attributes.
Study shows transfer of adversarial robustness between different perturbation types is limited.
problem Understanding adversarial robustness across various perturbation types.
method Evaluated 32 attacks of 5 different types on models trained on a subset of ImageNet.
result Adversarial robustness transfer between perturbation types is limited and depends on the specific type of perturbation.
This paper benchmarks neural network robustness to corruptions and perturbations.
problem Establishing benchmarks for image classifier robustness to corruptions and perturbations.
method Developed ImageNet-C and ImageNet-P datasets to evaluate robustness to corruptions and perturbations, not adversarial attacks.
result There are negligible changes in relative corruption robustness from AlexNet to ResNet classifiers.
Optimal Robust Estimation under Local and Global Corruptions: Stronger Adversary and Smaller Errorcs.DS
New algorithm optimizes robust estimation under mixed local and global corruptions.
problem Combining local and global corruptions in robust statistics.
method Information-theoretic approach using sliced-Wasserstein metric.
result Optimal error achieved in polynomial time for stronger local perturbations.
Study robust estimation of principal components under adversarial perturbations.
problem Estimating principal components in high-dimensional data under adversarial perturbations.
method Design of a computationally efficient algorithm for recovering the top-r principal subspace.
result The algorithm recovers an estimate of the top-r principal subspace with error depending on the robustness parameter κ.
New method for robustly interpreting ML models using quantile constraints and Wasserstein projections.
problem Assessing robustness of black-box models to input misspecification.
method Quantile-constrained Wasserstein projections for robust interpretability.
result Analytical solution for perturbation problem and smooth perturbations.
A new PCA algorithm removes bias from noisy data.
problem PCA in the presence of heteroskedastic noise.
method HeteroPCA algorithm iteratively imputes covariance matrix diagonal entries.
result Optimal under generalized spiked covariance model, proven computationally efficient.
Proposes a new framework to measure graph robustness.
problem Lack of control over perturbation strength in existing methods.
method Introduces weighted node perturbation with controllable strength and preserved graph topology.
result Extends robustness measure from statistics to graph properties.
This work analyzes how different forms of compressibility affect adversarial robustness in neural networks.
problem Understanding the interaction between compressibility and adversarial robustness in neural networks.
method Developed a principled framework to analyze the effects of neuron-level sparsity and spectral compressibility on adversarial robustness.
result Identified that different forms of compression can induce highly sensitive directions in the representation space that adversaries can exploit.
The paper analyzes adversarial training effects on classification accuracy.
problem Understanding adversarial training's impact on standard and robust accuracy.
method Derived precise statistical analysis for binary classification problems with Gaussian data.
result Theoretical explanation of standard and robust accuracy trends for adversarial training.
This paper improves flow models to better handle perturbations in real-world data.
problem Flow models amplify initial errors in perturbed data, leading to poor generalization.
method Utilizes Bernstein-type polynomials to construct Normalizing Flows (NF) for higher robustness.
result Proposed NF framework provides theoretical upper bounds and practical advantages.
New algorithms tackle robust RL with linear models, revealing unique challenges.
problem Distributionally robust offline RL with uncertainty in dynamics.
method Proposes minimax optimal and computationally efficient algorithms using novel function approximation mechanisms.
result Function approximation in robust offline RL is distinct and harder than in standard offline RL.
The paper provides robustness bounds for manifold learning techniques.
problem Understanding the robustness of manifold learning methods.
method Derives perturbation bounds for Procrustes, Classical Scaling, and Trilateration.
result Performance bounds for Isomap, Landmark Isomap, and Maximum Variance Unfolding are derived.
Batch normalization makes neural networks more vulnerable to small adversarial perturbations.
problem Adversarial vulnerability of neural networks trained with batch normalization.
method Investigated the impact of batch normalization on adversarial robustness and compared it to weight decay.
result Substituting weight decay for batch norm nullifies adversarial vulnerability.
The paper analyzes adversarial robustness for linear models and neural networks using Rademacher complexity.
problem Understanding adversarial robustness of linear models and neural networks.
method The paper uses Rademacher complexity to provide upper and lower bounds for adversarial robustness of linear hypotheses and neural networks.
result The paper provides bounds on adversarial Rademacher complexity for linear hypotheses and neural networks, offering a finer analysis of input dimensionality.
The paper assesses machine learning robustness with covariate perturbations.
problem Ensuring robustness of machine learning models against adversarial attacks and data changes.
method Proposes a framework using covariate perturbation techniques to assess model robustness.
result Demonstrates the effectiveness of the approach in comparing robustness across models and identifying instabilities.
WPCA improves subspace recovery robustness to outliers.
problem Improving subspace recovery in the presence of outliers.
method Winsorized PCA (WPCA) with theoretical analysis of accuracy and robustness.
result WPCA provides consistent subspace recovery from contaminated data.
Unified framework for learning from incomplete data under adversarial perturbations.
problem The role of unlabeled data in inference when the underlying distribution is adversarially perturbed.
method Unified learning framework combining Semi-Supervised Learning and Distributionally Robust Learning, with a novel generalization theory based on complexity measures.
result The method shows comparable performance to state-of-the-art on real-world datasets.
Adversarial training converges to robust neural networks.
problem Vulnerability of neural networks to adversarial examples.
method Adversarial training alternates minimization and maximization steps.
result Adversarial training finds a robust classifier close to optimal robust loss.
Paper establishes lower bounds for Gaussian process bandit optimization under various perturbation models.
problem Lower bounds for Gaussian process bandit optimization in noisy and robust settings.
method Novel proof techniques for standard and robust settings, including deterministic strategies.
result Demonstrates inevitable joint dependence of cumulative regret on corruption level and time horizon in robust settings.
Proposes a defense method against multiple adversarial video types.
problem Lack of multi-perturbation robustness in existing defense approaches.
method Adversarial training with multiple independent BN layers and a BN selection module.
result Demonstrates stronger multi-perturbation robustness against different adversarial video types.
The paper learns perturbation sets from data to improve robustness in machine learning.
problem Real-world perturbations are not well characterized in adversarial defenses.
method A conditional generator defines perturbation sets over latent space, with properties for quality measured.
result Learned perturbation sets generate diverse, meaningful perturbations and improve model robustness.
Develops a new robustness criterion for VAEs and provides theoretical guarantees.
problem Lack of formalization for robustness in VAEs.
method Introduces -robustness criterion and derives reconstruction margins.
result Derives theoretical guarantees for VAE robustness.
Semantify-NN verifies neural network robustness against semantic perturbations.
problem Verifying robustness of neural networks against semantic adversarial attacks.
method Inserting semantic perturbation layers (SP-layers) into neural networks to verify robustness.
result Semantify-NN significantly improves robustness verification performance over -norm-based methods.
PerturBench benchmarks ML models for cellular perturbation analysis.
problem Standardizing benchmarking in modeling single cell transcriptomic responses to perturbations.
method Modular platform, diverse datasets, metrics, extensive evaluation, rank metrics.
result Simpler models are competitive and scale well with larger datasets.
Study robustness of split conformal prediction under adversarial attacks.
problem Ensuring distribution-free coverage guarantees in CP under adversarial conditions.
method Theoretical analysis and extensive experiments on split conformal prediction robustness.
result Prediction coverage varies with calibration-time attack strength, enabling control over coverage under adversarial tests.