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.
Adaptive networks improve model robustness through conditional normalization.
Study stabilizes adversarial training in neural networks over infinite-dimensional spaces.
Study robustness of split conformal prediction under adversarial attacks.
Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to condition on to both the generator and discriminator. We show that this…
Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted adversarial examples, a new threat model where the attackers are not restricted to small…
We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adver…
Paper bounds convergence rate of adversarial surrogate risk.
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework, drawing on tools from the manifold reconstruction literature, to analyze the high-…
This work simplifies adversarial attacks using neural networks, reducing computation and improving training convergence.
Proposes a new GAN architecture for generating data conditioned on partial information.
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions. In this work, we propose an adversarial speaker verification (ASV) scheme to lear…
GANs involve training two networks in an adversarial game, where each network's task depends on its adversary. Recently, several works have framed GAN training as an online or continual learning problem. We focus on the discriminator, which must perform classification under an (adversarially) shifting data distribution…
Our work proves convergence to low robust training loss for polynomial width ReLU networks.
Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation. We show that demographic information of authors is encoded in -- and can be recovered from -- the intermediate representations learned by text-based neural classifiers. The …
Improved GAN training speed and quality with FastGAN.
We provide an approach for learning deep neural net representations of models described via conditional moment restrictions. Conditional moment restrictions are widely used, as they are the language by which social scientists describe the assumptions they make to enable causal inference. We formulate the problem of est…
Paper explores why overfitted DNNs in adversarial training can generalize.
Researchers develop PAIN to improve self-driving safety through adversarial training.
Deep neural networks have been widely deployed in various machine learning tasks. However, recent works have demonstrated that they are vulnerable to adversarial examples: carefully crafted small perturbations to cause misclassification by the network. In this work, we propose a novel defense mechanism called Boundary …
Paper introduces non-adversarial training for Neural SDEs using signature kernel scores.
Modern automatic speech recognition (ASR) systems need to be robust under acoustic variability arising from environmental, speaker, channel, and recording conditions. Ensuring such robustness to variability is a challenge in modern day neural network-based ASR systems, especially when all types of variability are not s…
TAET tackles long-tailed distributions in adversarial robustness.
Study non-asymptotic bounds for robust estimators under misspecified models.
New RL method improves robustness across various conditions.
We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We…
We propose a novel adversarial training method in feature space that improves model robustness and computational efficiency.
New method improves neural network robustness to adversarial attacks.
Boosting framework improves adversarial robustness in deep learning.
Bayes-optimal classifiers are robust to adversarial attacks, unlike CNNs trained on the same data.
Deep generative models are rapidly becoming a common tool for researchers and developers. However, as exhaustively shown for the family of discriminative models, the test-time inference of deep neural networks cannot be fully controlled and erroneous behaviors can be induced by an attacker. In the present work, we show…
Detects adversarial examples in deep speech recognition.
Generative adversarial networks (GANs) are a framework that learns a generative distribution through adversarial training. Recently, their class-conditional extensions (e.g., conditional GAN (cGAN) and auxiliary classifier GAN (AC-GAN)) have attracted much attention owing to their ability to learn the disentangled repr…
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…
In this paper we propose a data augmentation method for time series with irregular sampling, Time-Conditional Generative Adversarial Network (T-CGAN). Our approach is based on Conditional Generative Adversarial Networks (CGAN), where the generative step is implemented by a deconvolutional NN and the discriminative step…
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework, drawing on tools from the manifold reconstruction literature, to analyze the high-…
Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples () conditioned on both latent variables () and known auxiliary information (). We propose the Bidirectional cGAN (BiCoGAN), which effectively disentangles and in the generation process and provides a…
CGAN fails to improve deterministic sequence predictions, revealing a theoretical limitation.
New molecular design model outperforms existing methods.
Generative Adversarial Regression (GAR) learns risk scenarios robustly across policies.
Paper proposes a method to protect DCNNs from adversarial attacks and poor quality images.
One of the big restrictions in brain computer interface field is the very limited training samples, it is difficult to build a reliable and usable system with such limited data. Inspired by generative adversarial networks, we propose a conditional Deep Convolutional Generative Adversarial (cDCGAN) Networks method to ge…
Adversarial Regression uses GANs for non-linear regression with uncertainty estimation.
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains. Devising a definitive defense against such attacks is proven to be challenging, and the methods relying on detecting adversarial samples are only valid when the att…
The paper learns perturbation sets from data to improve robustness in machine learning.
Half-AVAE enhances VAE for underdetermined ICA with adversarial training.
Generative Adversarial Networks (GAN) have shown great promise in tasks like synthetic image generation, image inpainting, style transfer, and anomaly detection. However, generating discrete data is a challenge. This work presents an adversarial training based correlated discrete data (CDD) generation model. It also de…
Pairwise discriminators stabilize adversarial training by ensuring the generator's alignment is preserved.
Several dihedral angles prediction methods were developed for protein structure prediction and their other applications. However, distribution of predicted angles would not be similar to that of real angles. To address this we employed generative adversarial networks (GAN). Generative adversarial networks are composed …