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.
New adversarial examples with structured distortion sets improve robustness and perceptibility.
This paper introduces a new method to deceive causal structure learning by omitting data.
Study on robustness in linear regression models, focusing on adversarial perturbations.
New method GSAT improves robustness against structured perturbations.
Generative Adversarial Networks create synthetic data for structural damage detection.
When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks perturbing the raw input spaces may fail to capture structural information hidden in t…
DefenseVGAE defends graph neural networks against adversarial attacks.
New SSIM measure improves adversarial attacks' perceptual quality.
Adversarial examples are perturbed inputs designed to fool machine learning models. Most recent works on adversarial examples for image classification focus on directly modifying pixels with minor perturbations. A common requirement in all these works is that the malicious perturbations should be small enough (measured…
New method uses adversarial training for structural model estimation.
In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the unperturbed input, and yet are misclassified. In standard neural networks used for deep learning, atta…
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…
Pro-GNN defends graph neural networks from adversarial attacks by learning graph structure.
Adversarial training achieves optimal test error for shallow networks.
Graph Information Bottleneck (GIB) optimizes graph representations for robustness against adversarial attacks.
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the laten…
CANs improve GANs by enforcing structured constraints during training.
We propose Graphical Generative Adversarial Networks (Graphical-GAN) to model structured data. Graphical-GAN conjoins the power of Bayesian networks on compactly representing the dependency structures among random variables and that of generative adversarial networks on learning expressive dependency functions. We intr…
A new adversarial attack method using structured search and contextual bandits.
This work addresses dynamic KDE data structures with robustness to adversarial queries.
The representations learned by deep neural networks are difficult to interpret in part due to their large parameter space and the complexities introduced by their multi-layer structure. We introduce a method for computing persistent homology over the graphical activation structure of neural networks, which provides acc…
We derive upper and lower bounds for the policy regret of -round online learning problems with graph-structured feedback, where the adversary is nonoblivious but assumed to have a bounded memory. We obtain upper bounds of and for strongly-observable and weakly-observab…
The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks. However, despite the proliferation of such methods, there is currently no study of their robustness to adversarial attacks. We provide the first adversari…
Detects adversaries in crowdsourcing to improve accuracy.
Adversarial training is a useful approach to promote the learning of transferable representations across the source and target domains, which has been widely applied for domain adaptation (DA) tasks based on deep neural networks. Until very recently, existing adversarial domain adaptation (ADA) methods ignore the usefu…
Proposes a defense method against multiple adversarial video types.
Adversarial attacks found to be effective on code models.
This paper introduces a cross adversarial source separation (CASS) framework via autoencoder, a new model that aims at separating an input signal consisting of a mixture of multiple components into individual components defined via adversarial learning and autoencoder fitting. CASS unifies popular generative networks l…
We propose Progressive Structure-conditional Generative Adversarial Networks (PSGAN), a new framework that can generate full-body and high-resolution character images based on structural information. Recent progress in generative adversarial networks with progressive training has made it possible to generate high-resol…
New bounds show complexity of adversarial decision making.
DALI improves inference for GANs by matching prior and conditional distributions.
As a new approach to train generative models, \emph{generative adversarial networks} (GANs) have achieved considerable success in image generation. This framework has also recently been applied to data with graph structures. We propose labeled-graph generative adversarial networks (LGGAN) to train deep generative model…
Many predicted structured objects (e.g., sequences, matchings, trees) are evaluated using the F-score, alignment error rate (AER), or other multivariate performance measures. Since inductively optimizing these measures using training data is typically computationally difficult, empirical risk minimization of surrogate …
Paper proposes structured semantic perturbations to improve adversarial attacks.
Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper proposes ME-Net, a defense method that leverages matrix estimation (ME). In ME-Net, i…
Paper addresses hybrid learning with constrained adversaries, achieving optimal performance.
To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop new ways to defend against them. In this chapter, we describe the struct…
The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.
New geometric insights reveal properties of adversarial training problems.
Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.
A new method transfers adversarial robustness from teacher to student using feature distillation.
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 …
CleverHans is a software library that provides standardized reference implementations of adversarial example construction techniques and adversarial training. The library may be used to develop more robust machine learning models and to provide standardized benchmarks of models' performance in the adversarial setting. …
Graph neural networks are vulnerable to adversarial attacks by manipulating graph structure.
We propose two nonlinear regression methods, named Adversarial Orthogonal Regression (AdOR) for additive noise models and Adversarial Orthogonal Structural Equation Model (AdOSE) for the general case of structural equation models. Both methods try to make the residual of regression independent from regressors while put…
Paper explores tradeoff between standard and robust accuracy for latent models.
Half-AVAE enhances VAE for underdetermined ICA with adversarial training.
New method trims network data to resist adversarial contamination.