Interpolating label noise makes models vulnerable to adversarial attacks.
problem Adversarial vulnerability of models trained on noisy labels.
method Theoretical analysis of label noise and adversarial risk relationship.
result Uniform label noise induces adversarial risk similar to worst-case poisoning.
Label noise in adversarial training leads to robust overfitting, explained and mitigated.
problem Label noise in adversarial training causes robust overfitting.
method Proposed a method to automatically calibrate labels.
result Consistent performance improvements across various models and datasets.
Adversarial noises are linearly separable for random neural networks.
problem The challenge of adversarial examples in neural networks.
method Theoretical proof and empirical evidence for two-layer networks with random initialization and neural tangent kernel setup.
result Adversarial noises are linearly separable with corresponding labels.
Paper tackles robustness in adversarial noise with a meta-optimizer.
problem Sensitivity to adversarial noise hinders machine learning deployment.
method Meta-optimizer learns to robustly optimize models using adversarial examples.
result Meta-optimizer transfers adversarial knowledge to new models without generating new examples.
Colored noise improves neural network robustness against adversarial attacks.
problem Vulnerability of neural networks to adversarial perturbations.
method Injection of colored noise into network weights and activations during adversarial training.
result Our approach outperforms previous methods in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets.
Proposes a new model for noisy labels considering multiple labelers and adversarial attacks.
problem Real-world noisy label models with multiple labelers and adversarial attacks.
method Labeler-dependent noise model with adversarial attack vectors.
result State-of-the-art approaches for learning from noisy labels are defeated by adversarial label attacks.
Study efficient learning of robust halfspaces with noise.
problem Learning robust halfspaces in the presence of adversarial perturbations and random label noise.
method Provides conditions for robust learnability and a simple algorithm for any ℓ_p perturbation.
result Simple computationally efficient algorithm for robust learning with random label noise.
We present and study models of adversarial online learning where the feedback observed by the learner is noisy, and the feedback is either full information feedback or bandit feedback. Specifically, we consider binary losses xored with the noise, which is a Bernoulli random variable. We consider both a constant noise r…
New method enhances neural network robustness against adversarial attacks.
problem Enhancing neural network robustness against adversarial attacks.
method Variational framework with per-sample noise level selector.
result Enhanced empirical robustness and certified robustness.
Paper presents faster, robust adversarial training methods.
problem Increasing neural network robustness against adversarial attacks.
method Integrates FGSM with Pixelwise Noise Injection Layer (PNIL) and uniform noise.
result Achieves comparable results to PGD-based adversarial training but faster.
Deep neural networks (DNNs) have been widely used in the fields such as natural language processing, computer vision and image recognition. But several studies have been shown that deep neural networks can be easily fooled by artificial examples with some perturbations, which are widely known as adversarial examples. A…
SGD-trained neural networks generalize well even with adversarial label noise.
problem Generalization of neural networks trained on adversarial label noise.
method Training a one-hidden-layer neural network with SGD on arbitrary width networks.
result SGD-trained networks achieve classification accuracy competitive with the best halfspace over adversarial label noise.
Paper shows adversarial training can be fooled by new type of noise.
problem Adversarial training can be fooled by new types of noise.
method Designing ADVIN, a new type of inducing noise.
result ADVIN can degrade adversarial training robustness by 99.9%.
Convolutional neural networks (CNNs) are known for their good performance and generalization in vision-related tasks and have become state-of-the-art in both application and research-based domains. However, just like other neural network models, they suffer from a susceptibility to noise and adversarial attacks. An adv…
We introduce a new approach for designing computationally efficient learning algorithms that are tolerant to noise, and demonstrate its effectiveness by designing algorithms with improved noise tolerance guarantees for learning linear separators. We consider both the malicious noise model and the adversarial label nois…
Meta framework generates noise to improve multi-attack robustness.
problem Extraneous defense against single type of adversarial perturbation.
method Meta-learning framework with Meta Noise Generator (MNG).
result Significantly outperforms baselines across multiple perturbations.
Deep networks can overfit benignly but still be vulnerable to adversarial attacks.
problem Adversarial vulnerability of deep neural networks trained with benign overfitting.
method Investigated causes of adversarial vulnerability, identified label noise as a key factor, and explored the impact of training procedures and representation learning.
result Adversarial robustness requires more complex decision boundaries than simple ones, suggesting the need for better representation learning.
Many state-of-the-art machine learning models such as deep neural networks have recently shown to be vulnerable to adversarial perturbations, especially in classification tasks. Motivated by adversarial machine learning, in this paper we investigate the robustness of sparse regression models with strongly correlated co…
Adversarial training improves robustness of halfspaces in noisy data.
problem Learning robust halfspaces in the presence of label noise.
method Adversarial training with binary cross-entropy or nonconvex sigmoidal loss.
result Adversarial training yields robust halfspaces with improved classification error.
We introduce a Noise-based prior Learning (NoL) approach for training neural networks that are intrinsically robust to adversarial attacks. We find that the implicit generative modeling of random noise with the same loss function used during posterior maximization, improves a model's understanding of the data manifold …
The paper examines how adversarial training and noise affect neural network performance.
problem Overfitting in adversarial training and data augmentation.
method Adversarial training and data augmentation with noise in the context of regularized regression in RKHS.
result Appropriate regularization can prevent overfitting and improve performance.
Polynomial-time tester-learner for general halfspaces with Gaussian adversarial noise.
problem Learning general halfspaces with adversarial label noise.
method Reduction to testable learning of nearly homogeneous halfspaces.
result First polynomial time tester-learner for general halfspaces with dimension-independent misclassification error.
Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversar…
Adversarial training makes logistic regression weight loss landscapes sharper.
problem Understanding why adversarial training sharpens the weight loss landscape in logistic regression.
method Theoretical analysis of linear logistic regression model with L2 norm constraints, and experiments on ResNet18.
result Adversarial training sharpens the weight loss landscape in linear logistic regression models.
Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial examples---perturbed inputs specifically designed to produce intentional errors in the learning algorithms at test time. Existing input-agnostic adversarial perturbations exhibit interesting visual patterns that are currently unexplained…
Develops GLRT for defending against adversarial attacks in hypothesis testing.
problem Adversarial attacks on machine learning models causing misclassification.
method Generalized likelihood ratio test applied to composite hypothesis testing problem.
result GLRT approach yields competitive robustness-accuracy tradeoff under various attacks.
Polynomial-time algorithm for learning halfspaces with Gaussian-distributed data and adversarial noise.
problem Learning halfspaces in the presence of adversarial label noise.
method Iterative soft localization technique enhanced with appropriate testers.
result Output a halfspace with misclassification error $O(\opt)+\eps$.
Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. In this paper we present a novel study into adversarial attacks on deep reinforcement learning polic…
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…
NR-GANs learn clean images from noisy data.
problem Learning clean images from noisy training data.
method Introduced a noise generator and distribution/transformation constraints.
result NR-GANs can generate clean images from noisy data.
Efficiently learns a single neuron with adversarial noise, improving on prior work.
problem Learning a single neuron with adversarial label noise.
method Efficient algorithm using local error bounds from optimization theory.
result Approximates optimal L22-error within a constant factor. Non-convex SGD learns halfspaces with adversarial label noise efficiently.
problem Agnostically learning halfspaces in adversarial label noise settings.
method Non-convex SGD optimization for halfspace learning.
result Non-convex SGD achieves misclassification error close to optimal with adversarial noise.
Robust RL improves controller robustness to dynamics variations using adversarial populations.
problem Robustness issues in RL when dynamics are perturbed.
method Adversarial population augmentation to the Robust RL formulation.
result Population-based adversarial approach yields more robust and generalizable policies.
Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g. dropout, Gaussian noise) are missing in current Neural ODE networks. In this paper, we propose a new continuous ne…
Proposes MGPLL for PL learning with non-random noise.
problem Partial label learning with non-random label noise.
method Bi-directional mapping framework, conditional noise label generation, multi-class predictor, adversarial learning.
result Demonstrates state-of-the-art performance in partial label learning.
Research has shown that widely used deep neural networks are vulnerable to carefully crafted adversarial perturbations. Moreover, these adversarial perturbations often transfer across models. We hypothesize that adversarial weakness is composed of three sources of bias: architecture, dataset, and random initialization.…
The use of unsupervised data in addition to supervised data in training discriminative neural networks has improved the performance of this clas- sification scheme. However, the best results were achieved with a training process that is divided in two parts: first an unsupervised pre-training step is done for initializ…
Study improves robustness and sparsity in linear regression with adversarial outliers and heavy-tailed noise.
problem Outliers and heavy-tailed noise in linear regression coefficients.
method Sharp concentration inequalities and generic chaining.
result Sharper error bounds under weaker assumptions.
New algorithm learns halfspaces with adversarial noise efficiently.
problem Learning halfspaces in the presence of adversarial noise.
method Polynomial-time Perceptron-like online active learning algorithm.
result Near-optimal label and sample complexity with isotropic log-concave marginal distribution.
Quantum classification robustness improved via quantum hypothesis testing.
problem Vulnerability of quantum classification algorithms to input perturbations.
method Formalized link between quantum hypothesis testing and robustness, developed practical protocols.
result Tight robustness condition independent of noise source (natural or adversarial).
Robustly estimates linear regression coefficients with adversarial and noisy data.
problem Estimating robust linear regression coefficients with adversarial and noisy data.
method Adversarial robust weighted Huber regression with polynomial computational complexity.
result Derives an estimation error bound that depends on the stable rank and condition number of the covariance matrix.
Randomized smoothing reduces accuracy in ML models, especially at higher noise levels.
problem Adversarial attacks on ML models, especially randomized smoothing's accuracy drop.
method Theoretical and empirical analysis of randomized smoothing's effect on feasible hypotheses space.
result For some noise levels, randomized smoothing shrinks the set of feasible hypotheses, leading to accuracy drops.
Image classifiers often suffer from adversarial examples, which are generated by strategically adding a small amount of noise to input images to trick classifiers into misclassification. Over the years, many defense mechanisms have been proposed, and different researchers have made seemingly contradictory claims on the…
Detects and corrects adversarial images using image processing.
problem Vulnerability of deep neural networks to adversarial attacks.
method Image processing operations to detect and correct adversarial images.
result The method effectively detects and corrects adversarial images.
Unified framework improves neural network robustness against label noise and adversarial attacks.
problem High sensitivity of neural networks to data contamination, including label noises and adversarial perturbations.
method Unified minimum-divergence estimation problem, rSDNet framework.
result Improves robustness to label corruption and adversarial attacks while maintaining competitive accuracy on clean data.
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to adversarial example attack, which generates malicious output by adding slight perturbation…
New method handles uncertainty in adversarial attacks using ensemble noise simulation.
problem Uncertainty in adversarial attacks on neural networks.
method Simulates attacker's noisy perturbation using various gradient-based attack algorithms and a pre-processing Denoising Autoencoder (DAE) defense.
result Significant improvements in post-attack accuracy with the proposed ensemble-trained defense.
New method certifies robustness to sparse adversarial attacks.
problem Ensuring robustness of classifiers to sparse adversarial attacks.
method Randomized ablation of input features to provide robustness guarantees.
result Certifies robustness to sparse adversarial attacks with up to 31 pixels of distortion.