arXiv research

A game theory study on optimal hiding and searching strategies in discrete locations.

Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent strategy, many of which require sophisticated tool use and coordination. We find clea…

Survey on spectral gaps of random hyperbolic surfaces.

Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric informat…

Hides the complexity of neural networks, making them more transparent.

Optimizes trading in CFMMs and exchanges using deep learning.

AutoDIME automates design of multi-agent environments for RL.

Image steganography is a procedure for hiding messages inside pictures. While other techniques such as cryptography aim to prevent adversaries from reading the secret message, steganography aims to hide the presence of the message itself. In this paper, we propose a novel technique for hiding arbitrary binary data in i…

Matryoshka hides secret models in a carrier model, achieving high capacity and robustness.

Paper shows how to hide individuals in graphs to fool community detection models.

Steganography is the science of hiding a secret message within an ordinary public message, which is referred to as Carrier. Traditionally, digital signal processing techniques, such as least significant bit encoding, were used for hiding messages. In this paper, we explore the use of deep neural networks as steganograp…

The paper shows examples of 2-complexes that can't be embedded in R^4, hiding obstructions in higher Milnor invariants.

Neural networks are increasingly used for intrusion detection on industrial control systems (ICS). With neural networks being vulnerable to adversarial examples, attackers who wish to cause damage to an ICS can attempt to hide their attacks from detection by using adversarial example techniques. In this work we address…

Secret neural networks hidden within trained models.

Researchers found PP-GANs can hide sensitive data in sanitized images, undermining privacy checks.

Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. To address the privacy concerns of users in this environment, we propose a novel framework called PR-GAN that offers privacy-preserving mechanism using generative adversarial …

Challenge hides and seeks privacy in clinical time-series data.

HiDe learns hierarchical control for complex tasks by separating planning and control.

We consider a fundamental dynamic allocation problem motivated by the problem of $\textit{securities lending}$ in financial markets, the mechanism underlying the short selling of stocks. A lender would like to distribute a finite number of identical copies of some scarce resource to $n$ clients, each of whom has a priv…

Develops framework to analyze pruning of neural networks.

A novel approach to federated learning with strong privacy guarantees.

We propose an approach to fair classification that enforces independence between the classifier outputs and sensitive information by minimizing Wasserstein-1 distances. The approach has desirable theoretical properties and is robust to specific choices of the threshold used to obtain class predictions from model output…

Adversarial machine learning hides 5G communications from eavesdroppers.

We propose a privacy-enhanced matrix factorization recommender that exploits the fact that users can often be grouped together by interest. This allows a form of "hiding in the crowd" privacy. We introduce a novel matrix factorization approach suited to making recommendations in a shared group (or nym) setting and the …

Defense against small image patches using occlusions.

TIPRDC anonymizes data features to protect privacy while retaining useful information.

CycleGAN (Zhu et al. 2017) is one recent successful approach to learn a transformation between two image distributions. In a series of experiments, we demonstrate an intriguing property of the model: CycleGAN learns to "hide" information about a source image into the images it generates in a nearly imperceptible, high-…

Missing data imputation can help improve the performance of prediction models in situations where missing data hide useful information. This paper compares methods for imputing missing categorical data for supervised classification tasks. We experiment on two machine learning benchmark datasets with missing categorical…

The thesis tackles two stochastic control problems in capital structure and portfolio choice.

Framework explains deep learning candlestick recognition.

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…

Random flat bundles on surfaces have least eigenvalues at least 1/4.

Study minimax optimal RL in factored MDPs with bonus exploration.

Proposes QNN to protect input privacy in neural networks.

Glare is a phenomenon that occurs when the scene has a reflection of a light source or has one in it. This luminescence can hide useful information from the image, making text recognition virtually impossible. In this paper, we propose an approach to detect glare in images taken by users via mobile devices. Our method …

Most accurate recommender systems are black-box models, hiding the reasoning behind their recommendations. Yet explanations have been shown to increase the user's trust in the system in addition to providing other benefits such as scrutability, meaning the ability to verify the validity of recommendations. This gap bet…

Improved analysis for nonconvex SGD methods with flexible sampling.

Christoffel function characterizes the corruption a bounded-degree certificate cannot remove in robust halfspace learning.

We present heuristics for solving the maximin problem induced by the generative adversarial privacy setting for linear and convolutional neural network (CNN) adversaries. In the linear adversary setting, we present a greedy algorithm for approximating the optimal solution for the privatizer, which performs better as th…

This work presents the foundations of Singular Semi-Riemannian Geometry and Singular General Relativity, based on the author's research. An extension of differential geometry and of Einstein's equation to singularities is reported. Singularities of the form studied here allow a smooth extension of the Einstein field eq…

Is AdamW effective under heavy-tailed noise?

Given a model $f$ that predicts a target $y$ from a vector of input features $\pmb{x} = x_1, x_2, \ldots, x_M$, we seek to measure the importance of each feature with respect to the model's ability to make a good prediction. To this end, we consider how (on average) some measure of goodness or badness of prediction (wh…

Framework certifies fairness of machine learning models interactively and privately.

Time reversal invariance can be summarized as follows: no difference can be measured if a sequence of events is run forward or backward in time. Because price time series are dominated by a randomness that hides possible structures and orders, the existence of time reversal invariance requires care to be investigated. …

Paper proposes an online sparse linear regression method for streaming data.

Modeling a temporal process as if it is Markovian assumes the present encodes all of the process's history. When this occurs, the present captures all of the dependency between past and future. We recently showed that if one randomly samples in the space of structured processes, this is almost never the case. So, how d…

Recent studies have shown that information disclosed on social network sites (such as Facebook) can be used to predict personal characteristics with surprisingly high accuracy. In this paper we examine a method to give online users transparency into why certain inferences are made about them by statistical models, and …

Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to s…