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.
This paper proposes a new method to improve adversarial robustness of DNNs by focusing on semantic information.
This paper examines how adversarial perturbations affect model performance and equilibrium learning.
Simple regional perturbations maintain model transferability while reducing adversarial example distortion.
Restricted Boltzmann Machines (RBMs) are a class of generative neural network that are typically trained to maximize a log-likelihood objective function. We argue that likelihood-based training strategies may fail because the objective does not sufficiently penalize models that place a high probability in regions where…
PARADE generates provably robust adversarial examples for deep networks.
Adversarial training improves linear regression solutions, offering robustness against small perturbations.
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold and higher energies to other regions. Similar to the probabilistic GANs, a generator is seen as being trained to produce con…
The adversarial training procedure proposed by Madry et al. (2018) is one of the most effective methods to defend against adversarial examples in deep neural networks (DNNs). In our paper, we shed some lights on the practicality and the hardness of adversarial training by showing that the effectiveness (robustness on t…
Simplified trust region method reduces representation change during fine-tuning.
Generative Adversarial Networks (GAN) have shown promising results on a wide variety of complex tasks. Recent experiments show adversarial training provides useful gradients to the generator that helps attain better performance. In this paper, we intend to theoretically analyze whether supervised learning with adversar…
It has been shown that neural network classifiers are not robust. This raises concerns about their usage in safety-critical systems. We propose in this paper a regularization scheme for ReLU networks which provably improves the robustness of the classifier by maximizing the linear regions of the classifier as well as t…
The study reveals how adversarial perturbations can include class features for generalization.
New method removes MRI banding without post-processing.
Localized uncertainty attacks target uncertain regions to create imperceptible adversarial examples.
Enhances neural network robustness with polyhedral envelope regularization.
Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks are typically large and thus can be potentially detected. We propose a new black…
Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e.g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models. Since collecting new training data could be costly, we focus on better utilizing the given data by inducing t…
We explore adversarial robustness in the setting in which it is acceptable for a classifier to abstain---that is, output no class---on adversarial examples. Adversarial examples are small perturbations of normal inputs to a classifier that cause the classifier to give incorrect output; they present security and safety …
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-le…
Estimates the upper bound of linear regions in spheres centered at specific data points in ReLU neural networks.
Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tuning, or require many iterations to solve an optimization based adversarial attack. To address this problem, we present a new family of trus…
Deep neural networks' decision boundaries move closer to natural images during training.
Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and bio-informatics, where they have produced results comparable to human experts. However, th…
We propose a reinforcement learning solution to the \emph{soccer dribbling task}, a scenario in which a soccer agent has to go from the beginning to the end of a region keeping possession of the ball, as an adversary attempts to gain possession. While the adversary uses a stationary policy, the dribbler learns the best…
Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to adversarial manipulations at testing time. Specifically, suppose we have a testing …
Develops a new non-adversarial framework for better generative models.
Reliably detecting anomalies in a given set of images is a task of high practical relevance for visual quality inspection, surveillance, or medical image analysis. Autoencoder neural networks learn to reconstruct normal images, and hence can classify those images as anomalies, where the reconstruction error exceeds som…
SaliencyMix augments images with salient patches to improve model generalization.
New expressive losses improve adversarial robustness without sacrificing accuracy.
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…
Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive applications, including unmanned vehicles, drones, and video surveillance systems, onli…
Adaptive object detection method synthesizes target domain images from source domain images.
New approach makes adversarial examples less suspicious without changing perceptual salience.
Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable. A recent approach for finding a common representation of the two domains is via domain adversarial training (Ganin & Lempitsky, 2015), which attempt…
Adversarial robustness improved by abstaining from decisions.
Deep generative models improve global precipitation forecasts.
The paper learns perturbation sets from data to improve robustness in machine learning.
FROWN optimizes neural network robustness, improving safety in deep learning.
Study probabilistic safety of BNNs under adversarial attacks.
We study adversarial perturbations when the instances are uniformly distributed over . We study both "inherent" bounds that apply to any problem and any classifier for such a problem as well as bounds that apply to specific problems and specific hypothesis classes. As the current literature contains multiple…
Neural networks classify OOD images by their nearest neighbor in training data.
This paper studies adversarial attacks on Gaussian process bandits.
Proposes a method to identify critical regions in neural networks using adversarial attacks.
PaDGAN generates diverse, high-quality designs with improved performance.
Adversarial examples are considered a serious issue for safety critical applications of AI, such as finance, autonomous vehicle control and medicinal applications. Though significant work has resulted in increased robustness of systems to these attacks, systems are still vulnerable to well-crafted attacks. To address t…
RGI improves robustness of GAN-inversion for image restoration and anomaly detection.
AROS uses Lyapunov-stabilized embeddings to improve out-of-distribution detection robustness against adversarial attacks.
In this paper, we aim to solve for unsupervised domain adaptation of classifiers where we have access to label information for the source domain while these are not available for a target domain. While various methods have been proposed for solving these including adversarial discriminator based methods, most approache…