Adapting robust statistics to neural networks, researchers found neural networks can be more robust with certain loss functions.
problem The robustness of neural networks in complex learning tasks.
method Adapting the regression breakdown point from robust statistics to neural networks and comparing different configurations and contamination settings.
result Neural networks can benefit from robust loss functions, as demonstrated in extensive simulations.
Neural networks are becoming increasingly prevalent in software, and it is therefore important to be able to verify their behavior. Because verifying the correctness of neural networks is extremely challenging, it is common to focus on the verification of other properties of these systems. One important property, in pa…
Validates neural networks inputs to protect against adversarial examples.
problem Ensuring neural networks robustness against adversarial attacks.
method Runtime local robustness verification based on normal distribution of robustness radii.
result Improves neural network accuracy and protects against adversarial examples.
In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws intrinsic to the network structures. To address this problem and improve the robustness …
New method improves neural network robustness by identifying functions rather than parameters.
problem Neural networks' lack of robustness to distribution shifts.
method Identify the function represented by quadratic networks, not their parameters.
result Obtain robust generalization bounds for neural networks.
Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adversarial examples study has recently become very popular and it sometimes even reduces the term "adv…
GPUPoly verifies large neural networks robustly on GPUs.
problem Proving robustness of deep neural networks is crucial but challenging.
method Custom polyhedra algorithms on GPUs.
result GPUPoly can verify 1M neuron networks in 34.5 ms.
New model improves neural network robustness against input manipulations.
problem Improving neural network robustness against input manipulations.
method Causal view and deep causal manipulation augmented model (deep CAMA) with data augmentation and test-time fine-tuning.
result Deep CAMA shows superior robustness against unseen manipulations compared to traditional models.
1-Lipschitz networks are as accurate as classical networks and offer robustness.
problem Misconceptions about 1-Lipschitz neural networks and their properties.
method Analysis of 1-Lipschitz neural networks' accuracy, robustness, and generalization.
result 1-Lipschitz neural networks are as accurate as classical networks and can fit arbitrarily difficult boundaries.
A hybrid neural network improves robustness in estimating vehicle parameters from noisy data.
problem Estimating parameters of a mechanical vehicle model from noisy acceleration data.
method Introduced a convolutional neural network with two objective functions: naive and hybrid.
result The hybrid objective function outperforms the naive one in robustness on noisy input data.
NTK neural networks are robust to adversarial attacks in nonparametric regression.
problem Adversarial robustness of neural networks in nonparametric regression.
method Gradient flow with early stopping for NTK neural networks, proving robustness in Sobolev spaces.
result NTK neural networks achieve optimal adversarial robustness rates in Sobolev spaces.
In recent years, it has been found that neural networks can be easily fooled by adversarial examples, which is a potential safety hazard in some safety-critical applications. Many researchers have proposed various method to make neural networks more robust to white-box adversarial attacks, but an effective method have …
New mechanisms from primate vision improve neural network robustness.
problem Demonstrating robust neural networks to small adversarial perturbations.
method Investigated two biologically plausible mechanisms: non-uniform retina sampling and receptive field diversity.
result Non-uniform retina sampling and receptive field diversity improve adversarial robustness.
Convolutional and Recurrent, deep neural networks have been successful in machine learning systems for computer vision, reinforcement learning, and other allied fields. However, the robustness of such neural networks is seldom apprised, especially after high classification accuracy has been attained. In this paper, we …
Robust deep neural networks estimate multi-dimensional functional data robustly.
problem Estimating location function from multi-dimensional functional data robustly.
method Deep neural networks with ReLU activation, robust to outliers and model misspecification.
result Uniform convergence rates for robust deep neural network estimators.
Stochastic RNNs classify biological neural network paths with robust error bounds.
problem Classifying biological neural network paths.
method Modelled as a continuous-time stochastic recurrent neural network (RNN) with identity activation function, analysed in the robust regime.
result Generalisation error bound holds with high probability, showing the empirical risk minimiser is the best-in-class hypothesis.
New algorithm adds Hessian regularization to improve neural network robustness.
problem Improving neural network robustness against adversarial attacks.
method Proposes an efficient algorithm to train neural networks with Hessian operator-norm regularization.
result Hessian operator-norm regularization increases neural network robustness over input gradient regularization.
New method improves neural network robustness without sacrificing generalization.
problem Robustness and generalization are often at odds in neural networks.
method Distributionally robust loss function bridging robustness and generalization.
result Certified robustness against data evasion and poisoning attacks with guaranteed generalization.
This work improves certifiably robust models by distilling knowledge from adversarially robust teachers.
problem Certifiably robust models suffer from poor standard performance.
method Knowledge distillation from adversarially robust teachers to improve standard performance.
result Distillation from adversarially robust teachers consistently improves certified training performance.
Wider networks improve natural accuracy but worsen perturbation stability, affecting overall robustness.
problem Understanding the tradeoff between natural accuracy and perturbation stability in wider neural networks for adversarial robustness.
method Careful examination of the relationship between network width, robust regularization parameter λ, and perturbation stability using neural tangent kernels.
result Wider networks can achieve better natural accuracy but worse perturbation stability, leading to potentially worse overall model robustness.
Study robustness of polynomial neural networks using algebraic geometry.
problem Certify robustness radius of polynomial neural networks.
method Metric algebraic geometry, Euclidean distance degree, symbolic elimination, homotopy-continuation methods.
result Found decision boundaries with lower ED degree than generic cubic hypersurfaces.
Novel Bayesian neural network method for robustness.
problem Adversarial robustness without online training.
method Distributes uncertainty across all inputs.
result Demonstrates robustness on benchmark datasets.
New law establishes robustness for neural networks with bounded weights.
problem Ensuring robustness of neural networks against adversarial attacks.
method Deriving a lower bound on Lipschitz constant for arbitrary model classes with bounded Rademacher complexity.
result Established a law of robustness for weight-bounded neural networks, requiring log(n) layers for robust fitting.
HYDRA prunes robust neural networks to improve both benign and adversarial robustness.
problem Lack of robustness against adversarial attacks and large neural network size in deep learning.
method HYDRA integrates pruning techniques with adversarial training and verifiable robust training objectives.
result HYDRA achieves compressed networks with state-of-the-art benign and robust accuracy.
The robustness of neural networks to adversarial examples has received great attention due to security implications. Despite various attack approaches to crafting visually imperceptible adversarial examples, little has been developed towards a comprehensive measure of robustness. In this paper, we provide a theoretical…
CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we propose two extensions on this robustness score. First, we provide a new formal robustness guarantee for classifier functions that are twic…
Deterministic method for certifying neural network robustness.
problem Certifying neural network robustness against adversarial attacks.
method Equivalence between training and Gaussian averaging for robustness certification.
result Comparable certified accuracy and robustness to stochastic methods but with single model evaluation.
Proposes a framework for defining robustness in neural networks.
problem Lack of a precise foundation for robustness concepts in neural networks.
method Develops a rigorous and flexible framework based on mathematical postulates.
result Proposes new learning approaches for optimizing robustness objectives.
Recently, there has been an abundance of works on designing Deep Neural Networks (DNNs) that are robust to adversarial examples. In particular, a central question is which features of DNNs influence adversarial robustness and, therefore, can be to used to design robust DNNs. In this work, this problem is studied throug…
CNN-F uses generative feedback to improve neural networks' robustness to perturbations.
problem Neural networks' vulnerability to input perturbations like noise and attacks.
method Enforces self-consistency in neural networks by incorporating generative recurrent feedback.
result CNN-F shows significantly improved adversarial robustness compared to conventional CNNs.
An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatical…
Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to pruning literature, deep neural networks are known to be susceptible to adversarial…
Neural ordinary differential equations (ODEs) have been attracting increasing attention in various research domains recently. There have been some works studying optimization issues and approximation capabilities of neural ODEs, but their robustness is still yet unclear. In this work, we fill this important gap by expl…
This paper investigates how network width and depth affect adversarially robust DNNs.
problem Understanding architectural configurations for adversarially robust DNNs.
method Comprehensive investigation on the impact of network width and depth on adversarial robustness.
result Optimal architectural configuration for adversarial robustness exists and can improve robustness.
New method approximates neural network training for robustness.
problem Training robust neural networks with adversarial input perturbations.
method Stochastic convex optimization approach to adversarial training.
result Method achieves better adversarial robustness and performance.
Study shows prior Lipschitz continuity can improve adversarial robustness of Bayesian Neural Networks.
problem Improving adversarial robustness of Bayesian Neural Networks.
method Analysis of i.i.d., zero-mean Gaussian priors and posteriors approximated via mean-field variational inference.
result Adversarial robustness is sensitive to the prior variance.
New regularizers tighten convex relaxation bounds for neural networks.
problem Large gap between certifiable and empirical robustness in neural networks.
method Two regularizers to train neural networks yielding tighter convex relaxation bounds.
result Higher certified accuracy with proposed regularizers.
Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. We bound the distributionally robust risk for a model class rich enough to include deep neural networks by a regularised empirical risk invol…
Neural networks classify OOD images by their nearest neighbor in training data.
problem Understanding out-of-distribution prediction behavior of neural networks.
method Nearest category generalization (NCG) measure to assess OOD prediction accuracy.
result Adversarially robust networks have higher NCG accuracy than natural training, indicating local regularization impacts decision regions.
CAT improves robustness of neural networks by customizing perturbation levels.
problem Poor generalization of adversarial training on clean and perturbed data.
method CAT adapts perturbation level and label for each sample.
result CAT achieves better clean and robust accuracy than previous methods.
RATIO improves neural network robustness and explainability.
problem Neural networks' lack of robustness to adversarial changes and uncertainty on out-distribution samples.
method RATIO: Adversarial Training on In- and Out-distribution.
result RATIO leads to robust models with reliable confidence estimates on out-distribution samples.
This work explores how neural network architecture affects robustness to noisy labels.
problem The impact of neural network architecture on robustness to noisy labels.
method Formal framework connecting robustness to architecture alignments, measured by predictive power in representations.
result Network robustness to noisy labels improves when its architecture is more aligned with the target function.
Paper provides robustness bounds for GNNs against adversarial attacks.
problem Adversarial robustness of GNNs for graph-related tasks.
method PAC-Bayesian framework applied to GCN and MP-GNN.
result Spectral norms of diffusion matrix and weights govern robustness.
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.
Novel neural network approximates exact distance for robust classification.
problem Adversarial attacks on neural networks in safety-critical systems.
method Signed Distance Classifiers (SDCs) and Unitary-Gradient Neural Network.
result Approximates exact distance from classification boundary for certifiable predictions.
CaTs use DAGs with transformers to enforce causal constraints, improving neural network robustness.
problem Neural networks lack inherent causal structure respect, leading to reliability issues.
method Introducing Causal Transformers (CaTs) that operate under predefined causal constraints specified by DAGs.
result CaTs improve robustness and interpretability of neural networks under causal constraints.
The vulnerability to adversarial attacks has been a critical issue for deep neural networks. Addressing this issue requires a reliable way to evaluate the robustness of a network. Recently, several methods have been developed to compute robustness quantification for neural networks, namely, certified lower b…
Study on adversarial robustness in neural networks across initialization and training phases.
problem Understanding adversarial robustness in neural networks during different learning stages.
method Analyzes adversarial robustness in various scenarios of over-parameterized networks with quadratic targets and infinite samples.
result Robustness can worsen when test error improves, and vice versa, revealing new tradeoffs.