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.
Validates neural networks inputs to protect against adversarial examples.
Adversarial validation detects concept drift in user targeting systems.
OpenAlpha validates decentralized capital strategies using game theory and market aggregation.
CANs improve GANs by enforcing structured constraints during training.
Study robustness of split conformal prediction under adversarial attacks.
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…
Deep neural networks (DNNs) are notorious for their vulnerability to adversarial attacks, which are small perturbations added to their input images to mislead their prediction. Detection of adversarial examples is, therefore, a fundamental requirement for robust classification frameworks. In this work, we present a met…
Valid certifies LLMs' domain adherence, bounding out-of-domain behavior.
A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback-Leibler divergence. It is demonstrated that learning of the resulting symmetric VAE (sVAE) has close connections to previously developed adversarial-learning methods. This relationship helps unify the previously distinct techni…
RILA learns HQMMs robustly against adversarial corruption.
A Bayesian framework models adversarial uncertainty for robust machine learning.
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., -perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse …
Analyzes adversarial training's impact on loss landscape, proposing PAS to improve model performance.
New framework ensures valid uncertainty estimates for any data stream changes.
ACL improves robustness with unlabeled data, and we analyze its generalization using Rademacher complexity.
Paper develops robust Bayesian models for linear regression under adversarial perturbations.
AI attacks threaten insurance systems, requiring new defenses.
Adversarial training can lead to overfitting without compromising robustness.
We provide a bridge between generative modeling in the Machine Learning community and simulated physical processes in High Energy Particle Physics by applying a novel Generative Adversarial Network (GAN) architecture to the production of jet images -- 2D representations of energy depositions from particles interacting …
New method constrains CNN filter frequencies to improve robustness.
ADT improves model robustness by learning adversarial distributions.
Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into making any desired incorrect classification, potentially with very high certainty. Se…
Adversarial training can lead to unfair accuracy disparities between different groups.
Feature Squeezing is a recently proposed defense method which reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. It has been shown that feature squeezing defenses can be combined in a joint detection fram…
Proposes a new training algorithm for zero-sum games to avoid convergence issues.
Adaptive networks improve model robustness through conditional normalization.
The paper analyzes how generated data improves adversarial training in high-dimensional regression.
An intriguing property of deep neural networks is their inherent vulnerability to adversarial inputs, which significantly hinders their application in security-critical domains. Most existing detection methods attempt to use carefully engineered patterns to distinguish adversarial inputs from their genuine counterparts…
Theoretical study shows adversarial training improves robustness in deep learning models.
Deep Neural Networks(DNN) have excessively advanced the field of computer vision by achieving state of the art performance in various vision tasks. These results are not limited to the field of vision but can also be seen in speech recognition and machine translation tasks. Recently, DNNs are found to poorly fail when …
Blind single-channel source separation is a long standing signal processing challenge. Many methods were proposed to solve this task utilizing multiple signal priors such as low rank, sparsity, temporal continuity etc. The recent advance of generative adversarial models presented new opportunities in signal regression …
Advances AT with HE to improve model robustness.
Many machine learning models are vulnerable to adversarial attacks; for example, adding adversarial perturbations that are imperceptible to humans can often make machine learning models produce wrong predictions with high confidence. Moreover, although we may obtain robust models on the training dataset via adversarial…
Paper generates diverse, readable adversarial texts from scratch.
Randomized classifiers outperform deterministic ones in robustness against adversarial attacks.
PAC-Bayesian bounds estimate adversarial robustness.
We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the residual of the attention for remaining predictive signal. Motivated by the impo…
Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of -bounded and -minimal adversarial perturbations. However, the vulnerability of DNNs to adversarial perturbations with specific statistical properti…
Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The existing literature on provable adversarial robustness of models, however, exclu…
We study nonzero-sum hypothesis testing games that arise in the context of adversarial classification, in both the Bayesian as well as the Neyman-Pearson frameworks. We first show that these games admit mixed strategy Nash equilibria, and then we examine some interesting concentration phenomena of these equilibria. Our…
We ask whether the neural network interpretation methods can be fooled via adversarial model manipulation, which is defined as a model fine-tuning step that aims to radically alter the explanations without hurting the accuracy of the original models, e.g., VGG19, ResNet50, and DenseNet121. By incorporating the interpre…
New method protects neural networks from adversarial attacks without generating adversarial examples.
The paper evaluates machine learning cyber defenses using log data against adversarial attacks.
DALI improves inference for GANs by matching prior and conditional distributions.
State-of-the-art machine learning models frequently misclassify inputs that have been perturbed in an adversarial manner. Adversarial perturbations generated for a given input and a specific classifier often seem to be effective on other inputs and even different classifiers. In other words, adversarial perturbations s…
Adaptive framework generates challenging adversarial scenarios for autonomous vehicles.
Robust RL improves controller robustness to dynamics variations using adversarial populations.
Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical applications. In this paper, we conjecture that the leading cause of adversarial vulnerabili…