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.
Proposes a probabilistic method for generating semantically-aware adversarial examples.
Paper proposes adversarial modifications for link prediction models to improve robustness and interpretability.
The paper examines how to make multivariate estimators robust against adversarial data modifications.
Study shows how to manipulate VAEs for attacks and assess their robustness.
WM layer improves CNN robustness to noise and adversarial attacks.
Proposes a new method to generate unrestricted adversarial examples.
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to misclassify it. In many cases, these modifications can be so subtle that a …
This study examines when non-parametric methods are robust to adversarial examples.
The paper examines how to protect LASSO-based feature selection from adversarial attacks.
Despite the growing popularity of modern machine learning techniques (e.g. Deep Neural Networks) in cyber-security applications, most of these models are perceived as a black-box for the user. Adversarial machine learning offers an approach to increase our understanding of these models. In this paper we present an appr…
Training Generative Adversarial Networks (GANs) is notoriously challenging. We propose and study an architectural modification, self-modulation, which improves GAN performance across different data sets, architectures, losses, regularizers, and hyperparameter settings. Intuitively, self-modulation allows the intermedia…
Adversarial trading samples hurt financial markets.
Study makes code models robust to small changes that keep functionality.
Understanding and evaluating the robustness of neural networks under adversarial settings is a subject of growing interest. Attacks proposed in the literature usually work with models trained to minimize cross-entropy loss and output softmax probabilities. In this work, we present interesting experimental results that …
There is a growing body of literature showing that deep neural networks are vulnerable to adversarial input modification. Recently this work has been extended from image classification to malware classification over boolean features. In this paper we present several new methods for training restricted networks in this …
Method generates adversarial examples to improve classifier robustness.
Simple physical modifications can fool autonomous driving systems.
Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations and achieve high standard test accuracy. However, this is contrary to the stand…
We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during training which can be exploited at test time to force a neural network to exhibit abnor…
We study the problem of allocating stocks to dark pools. We propose and analyze an optimal approach for allocations, if continuous-valued allocations are allowed. We also propose a modification for the case when only integer-valued allocations are possible. We extend the previous work on this problem to adversarial sce…
As adversarial attacks pose a serious threat to the security of AI system in practice, such attacks have been extensively studied in the context of computer vision applications. However, few attentions have been paid to the adversarial research on automatic path finding. In this paper, we show dominant adversarial exam…
One pixel modification can make deep models unlearnable.
Label-Smoothing improves adversarial robustness of deep learning models.
Reduces transferability of adversarial examples between models.
Over the last few years, the phenomenon of adversarial examples --- maliciously constructed inputs that fool trained machine learning models --- has captured the attention of the research community, especially when the adversary is restricted to small modifications of a correctly handled input. Less surprisingly, image…
Study on adversarial examples and defenses for malware classification.
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically misleading the DNNs. Moreover, adversarial examples can be used to perform an attack on various kinds of DN…
Enhances single-step adversarial training to defend against iterative adversarial examples.
We propose an approach to distinguish between correct and incorrect image classifications. Our approach can detect misclassifications which either occur ("natural errors"), or due to ("adversarial errors"), both in a single . Our appr…
Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs). In this work, we first show that single generator GANs are unable to correctly model a distribution supported on…
Study on robustness of subspace learning from adversarial modifications.
We propose a learning-based filter that allows us to directly modify a synthetic speech waveform into a natural speech waveform. Speech-processing systems using a vocoder framework such as statistical parametric speech synthesis and voice conversion are convenient especially for a limited number of data because it is p…
Generative models create indistinguishable adversarial objects for object detection.
This work generates diverse adversarial attacks for different domains using latent variable perturbation.
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new clas…
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…
Recently, it has been shown that deep neural networks (DNN) are subject to attacks through adversarial samples. Adversarial samples are often crafted through adversarial perturbation, i.e., manipulating the original sample with minor modifications so that the DNN model labels the sample incorrectly. Given that it is al…
A simple modification improves GAN performance by discarding bad samples.
Novel method HAO mitigates Graph Injection Attack by preserving homophily.
Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. In a successful adversarial attack, the targeted mis-classification should be ach…
We study black-box attacks on machine learning classifiers where each query to the model incurs some cost or risk of detection to the adversary. We focus explicitly on minimizing the number of queries as a major objective. Specifically, we consider the problem of attacking machine learning classifiers subject to a budg…
A stealthy framework injects faults into DNNs to misclassify images without affecting overall accuracy.
This project improves model robustness to affine transformations.
New algorithms estimate matrix norms without matrix multiplication.
Study on detecting backdoor attacks using adversarial detection methods.
FDA3 defends IIoT applications against adversarial attacks by federating defense knowledge.
As machine learning algorithms continue to improve, there is an increasing need for explaining why a model produces a certain prediction for a certain input. In recent years, several methods for model interpretability have been developed, aiming to provide explanation of which subset regions of the model input is the m…
Pseudo-random number generators (PRNG) are a fundamental element of many security algorithms. We introduce a novel approach to their implementation, by proposing the use of generative adversarial networks (GAN) to train a neural network to behave as a PRNG. Furthermore, we showcase a number of interesting modifications…