Paper improves ATN for generating adversarial examples.
problem Generating adversarial examples to fool models.
method Improves Adversarial Transformation Networks (ATN).
result Won 2nd place in CAAD 2018 non-target task.
On-device research index
arXiv research
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “Adversarial Transformation Networks”
New bounds for classifier robustness to adversarial attacks.
problem Characterizing robustness of classifiers to adversarial perturbations.
method Introducing function transformations to relate adversarial risk to standard learning-theoretic risk bounds.
result Error rates on the same order as generalization error of original function classes.
Adversarial learning improves image augmentation for neural networks.
problem Improving data augmentation for neural networks with limited data.
method Adversarial learning using an encoder-decoder architecture with a spatial transformer network.
result Our approach outperforms previous generative data augmentation methods.
This research examines how data transformations affect adversarial robustness in recurrent neural networks.
problem Adversarial examples reduce machine learning accuracy, especially in high-dimensional datasets.
method Analysis of feature selection, dimensionality reduction, and trend extraction techniques on recurrent neural networks.
result Data transformations may increase vulnerability to adversarial samples, but only if they approximate intrinsic dimensionality and maintain manifold coverage.
Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networkscs.LG
This paper explores the trade-off between spatial and adversarial robustness in neural networks.
problem Understanding the trade-off between spatial and adversarial robustness in neural networks.
method Quantitative analysis and empirical testing with curriculum learning.
result Spatial robustness and adversarial robustness are quantitatively related and can be improved simultaneously.
Recent studies show that widely used deep neural networks (DNNs) are vulnerable to carefully crafted adversarial examples. Many advanced algorithms have been proposed to generate adversarial examples by leveraging the distance for penalizing perturbations. Researchers have explored different defense met…
This research shows adding regularization boosts accuracy and spatial robustness for adversarially transformed examples.
problem Improving accuracy and spatial robustness for adversarially transformed examples.
method Invariance-inducing regularization using worst-case transformations.
result Adding regularization on top of standard or adversarial training reduces relative error by 20% for CIFAR10 without increasing computational cost.
Paper trains models to resist string transformations.
problem Vulnerability of NLP models to adversarial string transformations.
method Combines search and abstraction techniques for robust training.
result Trained models resist combinations of user-defined transformations.
Study reveals how neural network biases align with adversarial attack frequencies.
problem Correlation between neural network biases and adversarial attacks.
method Fourier transform analysis of network implicit bias and adversarial perturbations.
result Network bias and adversarial attack frequencies are highly correlated.
New method improves graph representations against adversarial attacks.
problem Adversarial robustness in graph contrastive learning.
method Adversarial and edge insertion transformations.
result Promising results in preliminary experiments.
One Man's Trash is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examplescs.LG
Transform images with adversarial examples for robust classification.
problem Adversarial examples mislead deep neural networks in image classification.
method Transform input images with adversarial examples from a pre-trained model.
result Significantly more robust against a wide range of attacks compared to state-of-the-art methods.
Paper proposes transforming ATN to attack multivariate time series models.
problem Generating adversarial samples for multivariate time series classification models.
method Proposes using a distilled model as a surrogate to mimic attacked models and applies 1-NN DTW and FCN attacks.
result Both models were susceptible to attacks on all 18 datasets.
Paper proposes ATN to attack time series classification models.
problem Adversarial attacks on time series classification models.
method Adversarial transformation network (ATN) on a distilled model.
result Time series classification models are susceptible to adversarial attacks.
Paper presents a defense framework against adversarial examples.
problem Vulnerability of deep neural networks to adversarial examples.
method Cross-layer strategic ensemble defense with input and output transformations.
result Strategic ensemble defense achieves high defense success rates and robustness.
Convolutional Neural Networks with Transformed Input based on Robust Tensor Network Decompositioncs.LG
Tensor networks improve data privacy and robustness in convolutional neural networks.
problem Improving data privacy and robustness in convolutional neural networks.
method Tensor network decomposition for data partitioning and adversarial defense.
result Tensor networks can protect data privacy and resist adversarial attacks.
New method improves DNN robustness against adversarial attacks.
problem Adversarial vulnerability of neural networks.
method Enforcing linearity in DNN in transformed input and feature space, and augmenting with Local Lipschitz regularizer.
result Significantly improved robustness of DNN models on various datasets.
Study makes code models robust to small changes that keep functionality.
problem Vulnerability of deep neural networks to adversarial examples in source code.
method Defined a powerful adversary and adversarial training to learn robust models.
result Significant gains in robustness demonstrated across different languages and architectures.
New neural network method hides input information in complex-valued features to protect privacy.
problem Preventing adversaries from inferring input attributes from neural network features.
method Transforming real-valued features into complex-valued ones, making input hidden in a randomized phase.
result Significantly diminishes adversary's ability to infer input while preserving high accuracy.
PPD defends deep learning models against adversarial attacks using image permutations and Fourier phases.
problem Adversarial examples can mislead deep learning models.
method Combines random image permutation with Fourier phase components.
result Demonstrated state-of-the-art robustness against adversarial attacks.
Framework enhances DNNs against malware attacks.
problem Adversarial malware detection in DNNs.
method Hashing Transformation Deep Neural Networks (HashTran-DNN) with DAE regularizer.
result HashTran-DNN effectively defends against all four known attacks.
Local convolutions bias neural networks towards high-frequency adversarial examples.
problem High-frequency adversarial examples in neural networks.
method Analysis of different linear and nonlinear architectures, focusing on the impact of local convolution operations.
result Local convolutions induce an implicit bias towards high frequency features, leading to high-frequency adversarial examples.
New method enforces orthogonality in convolutional layers for improved robustness.
problem Improving adversarial robustness in deep learning models.
method Applying the Cayley transform to skew-symmetric convolutions in the Fourier domain.
result The proposed method preserves orthogonality and enhances adversarial robustness compared to existing techniques.
ForecastGAN: A Decomposition-Based Adversarial Framework for Multi-Horizon Time Series Forecastingcs.LG
ForecastGAN improves multi-horizon time series forecasting by integrating numerical and categorical features.
problem Limited performance of existing approaches in short-term and long-term forecasting.
method Decomposition, model selection, adversarial training.
result ForecastGAN consistently outperforms state-of-the-art transformer models for short-term forecasting.
The study uncovers invariant features in healthcare models that traditional methods overlook.
problem Discovering overlooked invariant features in healthcare models.
method Empirical learning of transformations minimizing Wasserstein distance and adding similarity regularization.
result LSTM models and BioBERT reveal invariant features not previously recognized.
Neural networks explained through geometric projections.
problem Understanding the geometric and mathematical underpinnings of neural networks.
method Exploiting connections between integration, Radon transforms, and neural networks.
result Distribution of neural network outputs can be interpreted as nonlinear projections along hypersurfaces.
Reinforcement learning (RL) has advanced greatly in the past few years with the employment of effective deep neural networks (DNNs) on the policy networks. With the great effectiveness came serious vulnerability issues with DNNs that small adversarial perturbations on the input can change the output of the network. Sev…
Guarantees recovery of compressible signals from adversarial noise.
problem Recovering compressible signals from noise and adversarial attacks.
method Extends adversarial defense framework to , , and norms.
result Recovery guarantees for various signal recovery methods under different noise types.
Post-averaging improves neural network robustness against adversarial attacks.
problem Adversarial attacks on neural networks.
method Post-averaging technique to smooth high frequency components.
result Post-averaging method successfully defends over 95% of adversarial samples without significant performance degradation.
Deep adversarial neural decodingq-bio.NC
Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning. Our approach first inverts the linear transformation from latent features to brain responses with maximum a posteriori estimation and then inverts the …
BUZz defends images from adversarial attacks using simple transformations.
problem Adversarial attacks on deep neural networks for image classification.
method Combination of deep neural networks and simple image transformations.
result Achieves significant improvement over state-of-the-art defenses with a modest drop in clean accuracy.
We extend GAN latent space projection for Gaussian priors.
problem Non-trivial latent space projection for GANs with Gaussian priors.
method Extend previous techniques to Gaussian priors.
result Demonstrated effectiveness of extended technique.
Stability training improves deep neural networks' robustness without data augmentation.
problem Improving deep neural networks' robustness against input perturbations.
method Stability training as an alternative to data augmentation.
result Stability training outperforms data augmentation in specific transformations and offers improved robustness against a broader range of distortions.
CWAN tackles multi-source heterogeneous domain adaptation with conditional weighting.
problem Learning cross-domain samples from multiple heterogeneous domains.
method CWAN uses a feature transformer, label classifier, and domain discriminator to learn from multiple sources.
result CWAN outperforms state-of-the-art methods on four real-world datasets.
This paper proposes a new method to approximate posterior distributions using generative neural networks trained via scoring rule minimization.
problem Bayesian Likelihood-Free Inference for models with intractable likelihood.
method Approximate posterior with generative neural networks trained via scoring rule minimization, avoiding the instability of adversarial training.
result Scoring Rule minimization leads to better performance and uncertainty quantification compared to adversarial training.
Closed-form polynomial approximations replace MLPs in transformers, enabling new interpretability methods.
problem Replacing MLPs with polynomial approximations for transformer models.
method Theoretical derivation of closed-form least-squares approximations of MLPs and GLUs using polynomial functions.
result Polynomial approximations explain over 95% of MLP and GLU outputs' variance, enabling interpretability.
Cross-Representation Transferability of Adversarial Attacks: From Spectrograms to Audio Waveformscs.SD
Adversarial attacks on spectrograms can fool audio classifiers trained on waveforms.
problem Susceptibility of audio classifiers to adversarial attacks on spectrograms.
method Applying adversarial attacks to spectrograms and reconstructing audio waveforms.
result Perturbed spectrograms can fool 2D CNNs and 1D CNNs trained on audio waveforms.
ChainGAN improves GANs by sequentially enhancing generated samples.
problem Current GANs learn transformations in one step, limiting their robustness and flexibility.
method ChainGAN uses a two-step process: a generator and a chain of editors.
result ChainGAN achieves competitive results on various datasets.
Generative Adversarial Networks generate realistic network traffic data.
problem Generating realistic flow-based network traffic for evaluation of NIDS.
method Generative Adversarial Networks (GANs) with preprocessing for categorical attributes.
result Two of three preprocessing methods generate high quality flow-based network traffic.
Paper develops a framework to protect data privacy using compressive adversarial methods.
problem Balancing data privacy and utility in data sharing.
method Optimal data releasing mechanism through convex optimization and nonlinear compression model.
result Demonstrates that compressive adversarial privacy can preserve sensitive information.
The paper uses differentiable rendering to generate semantic counterexamples for improving neural network robustness.
problem Neural networks' brittleness to semantic transformations.
method Differentiable rendering for generating realistic images that model semantic changes, combined with adversarial machine learning attacks.
result Semantic counterexamples improve generalization, robustness, and transferability of neural networks.
New algorithm defends against adversarial examples in image classification.
problem Defending against adversarial examples in image classification.
method Approximates Discrete Fourier transform of sparse signals corrupted by noise.
result Successfully defends against adversaries in image classification.
Adversarially trained transformers can learn robustly across tasks with minimal tuning.
problem Adversarial attacks and the high cost of adversarial training.
method Adversarial pretraining followed by in-context learning.
result Single-layer linear transformers can generalize robustly to unseen tasks.
Generative adversarial networks transform streetscape images to improve health and wellbeing.
problem Improving health and wellbeing outcomes through better streetscape design.
method Generative adversarial networks were used to translate Google Street View images, preserving structure while changing the style from bad health to good health areas.
result Translated images show that good health areas have more green space and compact urban design, while good social capital areas have more footpaths and less fencing.
Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood. We compute deep convolutional network generators by inverting a fixed embedding operator. Therefore, they do not require to be o…
ATPF combines PF and EnKF for better inference in complex systems.
problem Weight degeneracy in PF and approximation errors in EnKF.
method Adversarial learning to improve posterior matching and incorporate kernel methods for optimization.
result ATPF provides theoretical guarantees and practical advantages over PF and EnKF.
FAT-GAN simulates electron-proton scattering without theoretical assumptions.
problem Efficiently training GANs to simulate complex particle distributions.
method Developed FAT-GAN using transformed and augmented features to improve GAN performance.
result FAT-GAN accurately reproduces electron momenta distributions in electron-proton scattering.
Detects adversarial samples in DNNs using model mutation testing.
problem Vulnerability of DNNs to adversarial samples.
method Measures sensitivity of samples, uses statistical hypothesis testing and model mutation testing.
result Efficiently and accurately detects adversarial samples.
PARADE generates provably robust adversarial examples for deep networks.
problem Creating robust adversarial examples for deep neural networks.
method Iterative refinement of adversarial regions using optimization to ensure robustness under various perturbations.
result PARADE finds large, provably robust adversarial regions with high volume under various perturbations.