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.
Paper proposes a new black-box adversarial attack using normalizing flows.
AdvFlow generates imperceptible adversarial images using normalizing flows.
Flow-based generative models leverage invertible generator functions to fit a distribution to the training data using maximum likelihood. Despite their use in several application domains, robustness of these models to adversarial attacks has hardly been explored. In this paper, we study adversarial robustness of flow-b…
Gradient flow in ReLU networks biases towards generalization but makes them vulnerable to adversarial attacks.
NTK neural networks are robust to adversarial attacks in nonparametric regression.
Adversarial learning of probabilistic models has recently emerged as a promising alternative to maximum likelihood. Implicit models such as generative adversarial networks (GAN) often generate better samples compared to explicit models trained by maximum likelihood. Yet, GANs sidestep the characterization of an explici…
Proposes a new method to improve deep model security against adversarial deformations.
Gradient-trained shallow networks can generalize well but are vulnerable to small-radius adversarial attacks.
Study adversarial classification with data corruption up to ε, deriving geometric flows.
MonoFlow rethinks GANs using Wasserstein gradient flows.
Generative model simulates financial market price variations from order flow.
Flow-based data sets are necessary for evaluating network-based intrusion detection systems (NIDS). In this work, we propose a novel methodology for generating realistic flow-based network traffic. Our approach is based on Generative Adversarial Networks (GANs) which achieve good results for image generation. A major c…
Novel algorithm solves optimal transport using evolving probability distributions and convolution.
In the last couple of years, several adversarial attack methods based on different threat models have been proposed for the image classification problem. Most existing defenses consider additive threat models in which sample perturbations have bounded L_p norms. These defenses, however, can be vulnerable against advers…
This paper studies a training method to jointly estimate an energy-based model and a flow-based model, in which the two models are iteratively updated based on a shared adversarial value function. This joint training method has the following traits. (1) The update of the energy-based model is based on noise contrastive…
FCI method uses flow-based techniques to improve prediction confidence.
sFML learns stochastic dynamical systems from data.
This paper shows equivalence between SVGD and BBVI using kernel gradient flows.
A new method for aligning multiple distributions efficiently.
GeneraLight improves traffic signal control models' generalization ability.
Most random ReLU networks are vulnerable to small, Euclidean adversarial perturbations.
Detects adversarial examples using autoencoders at hidden layers.
Generative Adversarial Networks have been shown to be powerful in generating content. To this end, they have been studied intensively in the last few years. Nonetheless, training these networks requires solving a saddle point problem that is difficult to solve and slowly converging. Motivated from techniques in the reg…
Bayesian adversaries can outsmart traditional adversarial attacks.
We outline a detection method for adversarial inputs to deep neural networks. By viewing neural network computations as graphs upon which information flows from input space to out- put distribution, we compare the differences in graphs induced by different inputs. Specifically, by applying persistent homology to these …
The paper analyzes how GANs converge using dual metric flows.
Study compares adversarial regularization to sole supervision in machine learning.
Adversarial learning methods have been proposed for a wide range of applications, but the training of adversarial models can be notoriously unstable. Effectively balancing the performance of the generator and discriminator is critical, since a discriminator that achieves very high accuracy will produce relatively uninf…
Tackles dynamic subsurface flow via GAN with physical theory constraints.
Generative Adversarial Networks (GAN) training process, in most cases, apply Uniform or Gaussian sampling methods in the latent space, which probably spends most of the computation on examples that can be properly handled and easy to generate. Theoretically, importance sampling speeds up stochastic optimization in supe…
A new framework solves complex optimization problems with continuous worst-case distributions.
Generative adversarial networks reconstruct MRI images without full data.
We investigate artificial neural networks as a parametrization tool for stochastic inputs in numerical simulations. We address parametrization from the point of view of emulating the data generating process, instead of explicitly constructing a parametric form to preserve predefined statistics of the data. This is done…
This paper analyzes GANs using Fourier modes to stabilize training.
Any autoencoder network can be turned into a generative model by imposing an arbitrary prior distribution on its hidden code vector. Variational Autoencoder (VAE) [2] uses a KL divergence penalty to impose the prior, whereas Adversarial Autoencoder (AAE) [1] uses {\it generative adversarial networks} GAN [3]. GAN trade…
Recurrent Neural Networks (RNNs) yield attractive properties for constructing Intrusion Detection Systems (IDSs) for network data. With the rise of ubiquitous Machine Learning (ML) systems, malicious actors have been catching up quickly to find new ways to exploit ML vulnerabilities for profit. Recently developed adver…
Generative adversarial networks (GANs) were initially proposed to generate images by learning from a large number of samples. Recently, GANs have been used to emulate complex physical systems such as turbulent flows. However, a critical question must be answered before GANs can be considered trusted emulators for physi…
We develop an adversarial-reinforcement learning scheme for microswimmers in statistically homogeneous and isotropic turbulent fluid flows, in both two (2D) and three dimensions (3D). We show that this scheme allows microswimmers to find non-trivial paths, which enable them to reach a target on average in less time tha…
A method for estimating signal distributions from inverse problems using normalizing flows.
Turbulence is still one of the main challenges for accurately predicting reactive flows. Therefore, the development of new turbulence closures which can be applied to combustion problems is essential. Data-driven modeling has become very popular in many fields over the last years as large, often extensively labeled, da…
One of the main challenges in the parametrization of geological models is the ability to capture complex geological structures often observed in the subsurface. In recent years, generative adversarial networks (GAN) were proposed as an efficient method for the generation and parametrization of complex data, showing sta…
Diffusion LLMs can efficiently generate harmful prompts for adversarial testing.
Unified framework for SDMs and GANs with improved sampling and quality.
MI-GAN solves OPF with renewable uncertainty using model-informed layers.
This paper proposes a new method to approximate posterior distributions using generative neural networks trained via scoring rule minimization.
Method learns PDE dynamics via evolving latent manifold using Ricci flow.
This review compares various deep generative models.
In its simplest form, the traffic flow prediction problem is restricted to predicting a single time-step into the future. Multi-step traffic flow prediction extends this set-up to the case where predicting multiple time-steps into the future based on some finite history is of interest. This problem is significantly mor…