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.
T-BFA targets and misleads specific DNN inputs to a chosen output.
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…
LGV boosts adversarial attacks by improving surrogate models.
Characterizes deep neural network weight space for adversarial attacks.
The worst-case training principle that minimizes the maximal adversarial loss, also known as adversarial training (AT), has shown to be a state-of-the-art approach for enhancing adversarial robustness. Nevertheless, min-max optimization beyond the purpose of AT has not been rigorously explored in the adversarial contex…
Proposes SWA for adversarial training to improve model robustness.
Study shows adversarial attacks can fool speech-to-text models, and PCA is ineffective as a defense.
Neural networks trained with backpropagation, the standard algorithm of deep learning which uses weight transport, are easily fooled by existing gradient-based adversarial attacks. This class of attacks are based on certain small perturbations of the inputs to make networks misclassify them. We show that less biologica…
Study defends shallow neural networks from data-poisoning attacks.
This paper examines weight initialization for 1-Lipschitz networks to improve robustness against adversarial attacks.
This work studies adversarial transferability and proposes ensemble methods to improve robustness.
Simple aggregation of multiple methods defends against adversarial attacks on neural networks.
Recent advances show that deep neural networks are not robust to deliberately crafted adversarial examples which many are generated by adding human imperceptible perturbation to clear input. Consider norms attacks, Project Gradient Descent (PGD) and the Carlini and Wagner (C\&W) attacks are the two main methods, …
RoGAT enhances GAT robustness against adversarial attacks.
Paper examines adversarial attacks on weather forecasting models, focusing on TC trajectory prediction.
Colored noise improves neural network robustness against adversarial attacks.
MAT combines meta-learning and adversarial training to defend against universal patches.
We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convolution operations in CNNs commonly have structural sensitivity to specific noise composed of Fourier bas…
A new method improves adversarial robustness by optimizing importance weights.
Study examines uncertainty in adversarially trained models and proposes improved AT methods.
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can defeat both vanilla DNNs and those generated by various defense techniques develo…
DNN is presenting human-level performance for many complex intelligent tasks in real-world applications. However, it also introduces ever-increasing security concerns. For example, the emerging adversarial attacks indicate that even very small and often imperceptible adversarial input perturbations can easily mislead t…
Proposes SOVR loss to improve adversarial robustness by increasing logit margins.
Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under attacks. To combat this problem, techniques like adversarial training have been employed to obtain models which are robust on the training set. However, the …
Inspired by biophysical principles underlying nonlinear dendritic computation in neural circuits, we develop a scheme to train deep neural networks to make them robust to adversarial attacks. Our scheme generates highly nonlinear, saturated neural networks that achieve state of the art performance on gradient based adv…
Paper improves adversarial training using a learned optimizer.
Stablecoin system improves resilience to extreme market events.
In Machine Learning as a Service, a provider trains a deep neural network and gives many users access. The hosted (source) model is susceptible to model stealing attacks, where an adversary derives a surrogate model from API access to the source model. For post hoc detection of such attacks, the provider needs a robust…
Many machine learning models are vulnerable to adversarial attacks; for example, adding adversarial perturbations that are imperceptible to humans can often make machine learning models produce wrong predictions with high confidence. Moreover, although we may obtain robust models on the training dataset via adversarial…
Adversarial attacks against neural networks are a problem of considerable importance, for which effective defenses are not yet readily available. We make progress toward this problem by showing that non-negative weight constraints can be used to improve resistance in specific scenarios. In particular, we show that they…
Paper provides robustness bounds for GNNs against adversarial attacks.
Most random ReLU networks are vulnerable to small, Euclidean adversarial perturbations.
In this appraisal paper, we evaluate the efficacy of SHIELD, a compression-based defense framework for countering adversarial attacks on image classification models, which was published at KDD 2018. Here, we consider alternative threat models not studied in the original work, where we assume that an adaptive adversary …
The susceptibility of deep learning to adversarial attack can be understood in the framework of the Renormalisation Group (RG) and the vulnerability of a specific network may be diagnosed provided the weights in each layer are known. An adversary with access to the inputs and outputs could train a second network to clo…
Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challenge for the deployment of ML-based systems in safety- and security-critical environments like autonomous driving, disease detection or unmann…
Paper detects Trojan neural networks with limited or no data.
This paper studies adversarial attacks on Gaussian process bandits.
SWEEN improves certified robustness via weighted ensembling of smoothed classifiers.
Proposes a new video attack method that multiplies perturbation to improve model robustness.
Tricks adversarial attacks to target specific classes, improving classifier accuracy.
Automated discovery of adaptive attacks improves adversarial defense evaluation.
This work simplifies adversarial attacks using neural networks, reducing computation and improving training convergence.
We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player, zero-sum game between a learner and an adversary. In doing so, we illustrate the…
Study on detecting backdoor attacks using adversarial detection methods.
NP-Attack reduces query counts for black-box adversarial attacks.
We study the problem of defending deep neural network approaches for image classification from physically realizable attacks. First, we demonstrate that the two most scalable and effective methods for learning robust models, adversarial training with PGD attacks and randomized smoothing, exhibit very limited effectiven…
This paper analyzes adversarial attacks methods and their effectiveness.
Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy attacks. In this work we demonstrate how model inversion attacks, extracting trai…