arXiv research

Manipulating video content is easier than ever. Due to the misuse potential of manipulated content, multiple detection techniques that analyze the pixel data from the videos have been proposed. However, clever manipulators should also carefully forge the metadata and auxiliary header information, which is harder to do …

Pixle attacks images by rearranging pixels, bypassing neural networks.

PixL2R maps natural language to pixel-based rewards for RL, improving sample efficiency.

HO2 learns options from data efficiently, improving robot manipulation tasks.

Weak supervision enables learning causal representations from unstructured data.

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative approach is to have perturbations in the latent space. However, such perturbations ar…

FaceSigns embeds a secret watermark in images to authenticate and detect deepfakes.

Concept bottleneck models enable concept manipulation for model interpretation.

A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs…

Paper explores vulnerabilities in image authenticity detection methods, especially printing and scanning attacks.

Low-dimensional structure in images helps deep learning models generalize better.

Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming to mislead the predictions. Currently, the majority of these studies have focused on per…

Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception. While deep learning for perception has been shown to be vulnerable to a host of subtle adversarial…

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features, it does not provide an informative reward signal, leading to poor task performanc…

We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using the same learning algorithm, network architecture and hyper-parameters, our algo…

A rapidly growing area of work has studied the existence of adversarial examples, datapoints which have been perturbed to fool a classifier, but the vast majority of these works have focused primarily on threat models defined by $\ell_p$ norm-bounded perturbations. In this paper, we propose a new threat model for adver…

Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks are typically large and thus can be potentially detected. We propose a new black…

In blind hyperspectral unmixing (HU), the pure-pixel assumption is well-known to be powerful in enabling simple and effective blind HU solutions. However, the pure-pixel assumption is not always satisfied in an exact sense, especially for scenarios where pixels are heavily mixed. In the no pure-pixel case, a good blind…

Any subset of the plane can be approximated by a set of square pixels. This transition from a shape to its pixelation is rather brutal since it destroys geometric and topological information about the shape. Using a technique inspired by Morse Theory, we algorithmically produce a PL approximation of the original shape …

AI learns market manipulation through simulation, suggesting regulation.

Deep reinforcement learning (DRL) is capable of learning high-performing policies on a variety of complex high-dimensional tasks, ranging from video games to robotic manipulation. However, standard DRL methods often suffer from poor sample efficiency, partially because they aim to be entirely problem-agnostic. In this …

We develop a method for user-controllable semantic image inpainting: Given an arbitrary set of observed pixels, the unobserved pixels can be imputed in a user-controllable range of possibilities, each of which is semantically coherent and locally consistent with the observed pixels. We achieve this using a deep generat…

The paper analyzes how leverage affects manipulation in event-linked markets, offering new insights into regulation.

New model improves neural network robustness against input manipulations.

Many machine learning image classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Current adversarial methods directly alter pixel colors and evaluate against pixel norm-balls: pixel perturbations smaller than a specified magnitude, according t…

Pixel-space diffusion models outperform latent models on high-resolution image synthesis.

This paper studies poisoning attacks in episodic RL and discovers their effectiveness depends on reward bounds.

Herein, we present a system for hyperspectral image segmentation that utilizes multiple class--based denoising autoencoders which are efficiently trained. Moreover, we present a novel hyperspectral data augmentation method for labelled HSI data using linear mixtures of pixels from each class, which helps the system wit…

Improves spline quality and accuracy in computational microscopy.

Semantic inpainting is the task of inferring missing pixels in an image given surrounding pixels and high level image semantics. Most semantic inpainting algorithms are deterministic: given an image with missing regions, a single inpainted image is generated. However, there are often several plausible inpaintings for a…

Blind source separation is a common processing tool to analyse the constitution of pixels of hyperspectral images. Such methods usually suppose that pure pixel spectra (endmembers) are the same in all the image for each class of materials. In the framework of remote sensing, such an assumption is no more valid in the p…

Deep neural networks were shown to be vulnerable to single pixel modifications. However, the reason behind such phenomena has never been elucidated. Here, we propose Propagation Maps which show the influence of the perturbation in each layer of the network. Propagation Maps reveal that even in extremely deep networks s…

In multi-temporal SAR interferometry (MT-InSAR), persistent scatterer (PS) pixels are used to estimate geophysical parameters, essentially deformation. Conventionally, PS pixels are selected on the basis of the estimated noise present in the spatially uncorrelated phase component along with look-angle error in a tempor…

In this work we propose a model that can manipulate individual visual attributes of objects in a real scene using examples of how respective attribute manipulations affect the output of a simulation. As an example, we train our model to manipulate the expression of a human face using nonphotorealistic 3D renders of a f…

Prediction markets can be manipulated by traders who can move contract settlements, harming price discovery.

DIGIT is a low-cost tactile sensor for in-hand manipulation.

Evolutionary algorithm finds optimal pixel perturbations to improve neural network generalization.

Volunteer labor can temporarily yield lower benefits to charities than its costs. In such instances, organizations may wish to defer volunteer donations to a later date. Exploiting a discontinuity in blood donations' eligibility criteria, we show that deferring donors reduces their future volunteerism. In our setting, …

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 $\mathcal{L}_p$ distance for penalizing perturbations. Researchers have explored different defense met…

Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of data manipulation. In this work, we propose a new method that supports learning d…

Paper presents a new port-Hamiltonian model for vehicle manipulators.

Optimal benchmark design varies based on costs in financial manipulation.

Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base classifications on randomly noised samples where the noise is additive. In this pap…

Study examines reasons for Nutek India's share price drop.

DEceit constructs effective universal pixel-restricted perturbations for deep image classifiers.

Simple image augmentation boosts deep RL from pixels.

New method uses statistical physics to detect financial market manipulation.

Given the ability to directly manipulate image pixels in the digital input space, an adversary can easily generate imperceptible perturbations to fool a Deep Neural Network (DNN) image classifier, as demonstrated in prior work. In this work, we propose ShapeShifter, an attack that tackles the more challenging problem o…