arXiv subjects

Peter Hall

Publications and source records attributed to Peter Hall.

At least 19 recordsLinked to original sources

arXiv2025

The Pitfalls of "Security by Obscurity" And What They Mean for Transparent AI

Calls for transparency in AI systems are growing in number and urgency from diverse stakeholders ranging from regulators to researchers to users (with a comparative absence of companies developing AI). Notions of transparency for AI abound, each addressing distinct interests and concerns. In computer security, transparency is likewise regarded as a key concept. The security community has for decades pushed back against so-called security by obscurity -- the idea that hiding how a system works protects it from attack -- against significant pressure from industry and other stakeholders. Over the decades, in a community process that is imperfect and ongoing, security researchers and practitioners have gradually built up some norms and practices around how to balance transparency interests with possible negative side effects. This paper asks: What insights can the AI community take from the security community's experience with transparency? We identify three key themes in the security community's perspective on the benefits of transparency and their approach to balancing transparency against countervailing interests. For each, we investigate parallels and insights relevant to transparency in AI. We then provide a case study discussion on how transparency has shaped the research subfield of anonymization. Finally, shifting our focus from similarities to differences, we highlight key transparency issues where modern AI systems present challenges different from other kinds of security-critical systems, raising interesting open questions for the security and AI communities alike.

cs.CR↗

arXiv2024

A Meta-Complexity Characterization of Quantum Cryptography

We prove the first meta-complexity characterization of a quantum cryptographic primitive. We show that one-way puzzles exist if and only if there is some quantum samplable distribution of binary strings over which it is hard to approximate Kolmogorov complexity. Therefore, we characterize one-way puzzles by the average-case hardness of a uncomputable problem. This brings to the quantum setting a recent line of work that characterizes classical cryptography with the average-case hardness of a meta-complexity problem, initiated by Liu and Pass. Moreover, since the average-case hardness of Kolmogorov complexity over classically polynomial-time samplable distributions characterizes one-way functions, this result poses one-way puzzles as a natural generalization of one-way functions to the quantum setting. Furthermore, our equivalence goes through probability estimation, giving us the additional equivalence that one-way puzzles exist if and only if there is a quantum samplable distribution over which probability estimation is hard. We also observe that the oracle worlds of defined by Kretschmer et. al. rule out any relativizing characterization of one-way puzzles by the hardness of a problem in NP or QMA, which means that it may not be possible with current techniques to characterize one-way puzzles with another meta-complexity problem.

cs.CR↗

arXiv2023

On the Computational Hardness of Quantum One-Wayness

There is a large body of work studying what forms of computational hardness are needed to realize classical cryptography. In particular, one-way functions and pseudorandom generators can be built from each other, and thus require equivalent computational assumptions to be realized. Furthermore, the existence of either of these primitives implies that $\rm{P} \neq \rm{NP}$, which gives a lower bound on the necessary hardness. One can also define versions of each of these primitives with quantum output: respectively one-way state generators and pseudorandom state generators. Unlike in the classical setting, it is not known whether either primitive can be built from the other. Although it has been shown that pseudorandom state generators for certain parameter regimes can be used to build one-way state generators, the implication has not been previously known in full generality. Furthermore, to the best of our knowledge, the existence of one-way state generators has no known implications in complexity theory. We show that pseudorandom states compressing $n$ bits to $\log n + 1$ qubits can be used to build one-way state generators and pseudorandom states compressing $n$ bits to $\omega(\log n)$ qubits are one-way state generators. This is a nearly optimal result since pseudorandom states with fewer than $c \log n$-qubit output can be shown to exist unconditionally. We also show that any one-way state generator can be broken by a quantum algorithm with classical access to a $\rm{PP}$ oracle. An interesting implication of our results is that a $t(n)$-copy one-way state generator exists unconditionally, for every $t(n) = o(n/\log n)$. This contrasts nicely with the previously known fact that $O(n)$-copy one-way state generators require computational hardness. We also outline a new route towards a black-box separation between one-way state generators and quantum bit commitments.

cs.CR↗

arXiv2022

Nonlinear Equivariant Imaging: Learning Multi-Parametric Tissue Mapping without Ground Truth for Compressive Quantitative MRI

Current state-of-the-art reconstruction for quantitative tissue maps from fast, compressive, Magnetic Resonance Fingerprinting (MRF), use supervised deep learning, with the drawback of requiring high-fidelity ground truth tissue map training data which is limited. This paper proposes NonLinear Equivariant Imaging (NLEI), a self-supervised learning approach to eliminate the need for ground truth for deep MRF image reconstruction. NLEI extends the recent Equivariant Imaging framework to nonlinear inverse problems such as MRF. Only fast, compressed-sampled MRF scans are used for training. NLEI learns tissue mapping using spatiotemporal priors: spatial priors are obtained from the invariance of MRF data to a group of geometric image transformations, while temporal priors are obtained from a nonlinear Bloch response model approximated by a pre-trained neural network. Tested retrospectively on two acquisition settings, we observe that NLEI (self-supervised learning) closely approaches the performance of supervised learning, despite not using ground truth during training.

eess.IV↗

arXiv2022

A Plug-and-Play Approach to Multiparametric Quantitative MRI: Image Reconstruction using Pre-Trained Deep Denoisers

Current spatiotemporal deep learning approaches to Magnetic Resonance Fingerprinting (MRF) build artefact-removal models customised to a particular k-space subsampling pattern which is used for fast (compressed) acquisition. This may not be useful when the acquisition process is unknown during training of the deep learning model and/or changes during testing time. This paper proposes an iterative deep learning plug-and-play reconstruction approach to MRF which is adaptive to the forward acquisition process. Spatiotemporal image priors are learned by an image denoiser i.e. a Convolutional Neural Network (CNN), trained to remove generic white gaussian noise (not a particular subsampling artefact) from data. This CNN denoiser is then used as a data-driven shrinkage operator within the iterative reconstruction algorithm. This algorithm with the same denoiser model is then tested on two simulated acquisition processes with distinct subsampling patterns. The results show consistent de-aliasing performance against both acquisition schemes and accurate mapping of tissues' quantitative bio-properties. Software available: https://github.com/ketanfatania/QMRI-PnP-Recon-POC

eess.IV↗

arXiv2020

Geometric Style Transfer

Neural style transfer (NST), where an input image is rendered in the style of another image, has been a topic of considerable progress in recent years. Research over that time has been dominated by transferring aspects of color and texture, yet these factors are only one component of style. Other factors of style include composition, the projection system used, and the way in which artists warp and bend objects. Our contribution is to introduce a neural architecture that supports transfer of geometric style. Unlike recent work in this area, we are unique in being general in that we are not restricted by semantic content. This new architecture runs prior to a network that transfers texture style, enabling us to transfer texture to a warped image. This form of network supports a second novelty: we extend the NST input paradigm. Users can input content/style pair as is common, or they can chose to input a content/texture-style/geometry-style triple. This three image input paradigm divides style into two parts and so provides significantly greater versatility to the output we can produce. We provide user studies that show the quality of our output, and quantify the importance of geometric style transfer to style recognition by humans.

cs.CV↗

arXiv2020

VGPN: Voice-Guided Pointing Robot Navigation for Humans

Pointing gestures are widely used in robot navigationapproaches nowadays. However, most approaches only use point-ing gestures, and these have two major limitations. Firstly, they need to recognize pointing gestures all the time, which leads to long processing time and significant system overheads. Secondly,the user's pointing direction may not be very accurate, so the robot may go to an undesired place. To relieve these limitations,we propose a voice-guided pointing robot navigation approach named VGPN, and implement its prototype on a wheeled robot,TurtleBot 2. VGPN recognizes a pointing gesture only if voice information is insufficient for navigation. VGPN also uses voice information as a supplementary channel to help determine the target position of the user's pointing gesture. In the evaluation,we compare VGPN to the pointing-only navigation approach. The results show that VGPN effectively reduces the processing timecost when pointing gesture is unnecessary, and improves the usersatisfaction with navigation accuracy.

cs.RO↗

arXiv2019

Artistic Domain Generalisation Methods are Limited by their Deep Representations

The cross-depiction problem refers to the task of recognising visual objects regardless of their depictions; whether photographed, painted, sketched, {\em etc}. In the past, some researchers considered cross-depiction to be domain adaptation (DA). More recent work considers cross-depiction as domain generalisation (DG), in which algorithms extend recognition from one set of domains (such as photographs and coloured artwork) to another (such as sketches). We show that fixing the last layer of AlexNet to random values provides a performance comparable to state of the art DA and DG algorithms, when tested over the PACS benchmark. With support from background literature, our results lead us to conclude that texture alone is insufficient to support generalisation; rather, higher-order representations such as structure and shape are necessary.

cs.CV↗

arXiv2019

Rank3DGAN: Semantic mesh generation using relative attributes

In this paper, we investigate a novel problem of using generative adversarial networks in the task of 3D shape generation according to semantic attributes. Recent works map 3D shapes into 2D parameter domain, which enables training Generative Adversarial Networks (GANs) for 3D shape generation task. We extend these architectures to the conditional setting, where we generate 3D shapes with respect to subjective attributes defined by the user. Given pairwise comparisons of 3D shapes, our model performs two tasks: it learns a generative model with a controlled latent space, and a ranking function for the 3D shapes based on their multi-chart representation in 2D. The capability of the model is demonstrated with experiments on HumanShape, Basel Face Model and reconstructed 3D CUB datasets. We also present various applications that benefit from our model, such as multi-attribute exploration, mesh editing, and mesh attribute transfer.

cs.CV↗

arXiv2018

What and Where: A Context-based Recommendation System for Object Insertion

In this work, we propose a novel topic consisting of two dual tasks: 1) given a scene, recommend objects to insert, 2) given an object category, retrieve suitable background scenes. A bounding box for the inserted object is predicted in both tasks, which helps downstream applications such as semi-automated advertising and video composition. The major challenge lies in the fact that the target object is neither present nor localized at test time, whereas available datasets only provide scenes with existing objects. To tackle this problem, we build an unsupervised algorithm based on object-level contexts, which explicitly models the joint probability distribution of object categories and bounding boxes with a Gaussian mixture model. Experiments on our newly annotated test set demonstrate that our system outperforms existing baselines on all subtasks, and do so under a unified framework. Our contribution promises future extensions and applications.

cs.CV↗

arXiv2018

LineNet: a Zoomable CNN for Crowdsourced High Definition Maps Modeling in Urban Environments

High Definition (HD) maps play an important role in modern traffic scenes. However, the development of HD maps coverage grows slowly because of the cost limitation. To efficiently model HD maps, we proposed a convolutional neural network with a novel prediction layer and a zoom module, called LineNet. It is designed for state-of-the-art lane detection in an unordered crowdsourced image dataset. And we introduced TTLane, a dataset for efficient lane detection in urban road modeling applications. Combining LineNet and TTLane, we proposed a pipeline to model HD maps with crowdsourced data for the first time. And the maps can be constructed precisely even with inaccurate crowdsourced data.

cs.CV↗

arXiv2018

Ranking CGANs: Subjective Control over Semantic Image Attributes

In this paper, we investigate the use of generative adversarial networks in the task of image generation according to subjective measures of semantic attributes. Unlike the standard (CGAN) that generates images from discrete categorical labels, our architecture handles both continuous and discrete scales. Given pairwise comparisons of images, our model, called RankCGAN, performs two tasks: it learns to rank images using a subjective measure; and it learns a generative model that can be controlled by that measure. RankCGAN associates each subjective measure of interest to a distinct dimension of some latent space. We perform experiments on UT-Zap50K, PubFig and OSR datasets and demonstrate that the model is expressive and diverse enough to conduct two-attribute exploration and image editing.

cs.CV↗

arXiv2018

A frequency domain analysis of the error distribution from noisy high-frequency data

Data observed at high sampling frequency are typically assumed to be an additive composite of a relatively slow-varying continuous-time component, a latent stochastic process or a smooth random function, and measurement error. Supposing that the latent component is an It\^{o} diffusion process, we propose to estimate the measurement error density function by applying a deconvolution technique with appropriate localization. Our estimator, which does not require equally-spaced observed times, is consistent and minimax rate optimal. We also investigate estimators of the moments of the error distribution and their properties, propose a frequency domain estimator for the integrated volatility of the underlying stochastic process, and show that it achieves the optimal convergence rate. Simulations and a real data analysis validate our analysis.

math.ST↗

arXiv2017

The detection of an extremely bright fast radio burst in a phased array feed survey

We report the detection of an ultra-bright fast radio burst (FRB) from a modest, 3.4-day pilot survey with the Australian Square Kilometre Array Pathfinder. The survey was conducted in a wide-field fly's-eye configuration using the phased-array-feed technology deployed on the array to instantaneously observe an effective area of $160$ deg$^2$, and achieve an exposure totaling $13200$ deg$^2$ hr. We constrain the position of FRB 170107 to a region $8'\times8'$ in size (90% containment) and its fluence to be $58\pm6$ Jy ms. The spectrum of the burst shows a sharp cutoff above $1400$ MHz, which could be either due to scintillation or an intrinsic feature of the burst. This confirms the existence of an ultra-bright ($>20$ Jy ms) population of FRBs.

astro-ph.HE↗

arXiv2016

Detecting People in Artwork with CNNs

CNNs have massively improved performance in object detection in photographs. However research into object detection in artwork remains limited. We show state-of-the-art performance on a challenging dataset, People-Art, which contains people from photos, cartoons and 41 different artwork movements. We achieve this high performance by fine-tuning a CNN for this task, thus also demonstrating that training CNNs on photos results in overfitting for photos: only the first three or four layers transfer from photos to artwork. Although the CNN's performance is the highest yet, it remains less than 60\% AP, suggesting further work is needed for the cross-depiction problem. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-46604-0_57

cs.CV↗

arXiv2016

Dense Motion Estimation for Smoke

Motion estimation for highly dynamic phenomena such as smoke is an open challenge for Computer Vision. Traditional dense motion estimation algorithms have difficulties with non-rigid and large motions, both of which are frequently observed in smoke motion. We propose an algorithm for dense motion estimation of smoke. Our algorithm is robust, fast, and has better performance over different types of smoke compared to other dense motion estimation algorithms, including state of the art and neural network approaches. The key to our contribution is to use skeletal flow, without explicit point matching, to provide a sparse flow. This sparse flow is upgraded to a dense flow. In this paper we describe our algorithm in greater detail, and provide experimental evidence to support our claims.

cs.CV↗

arXiv2016

Nonparametric covariate-adjusted regression

We consider nonparametric estimation of a regression curve when the data are observed with multiplicative distortion which depends on an observed confounding variable. We suggest several estimators, ranging from a relatively simple one that relies on restrictive assumptions usually made in the literature, to a sophisticated piecewise approach that involves reconstructing a smooth curve from an estimator of a constant multiple of its absolute value, and which can be applied in much more general scenarios. We show that, although our nonparametric estimators are constructed from predictors of the unobserved undistorted data, they have the same first order asymptotic properties as the standard estimators that could be computed if the undistorted data were available. We illustrate the good numerical performance of our methods on both simulated and real datasets.

math.ST↗

arXiv2015

The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs

The cross-depiction problem is that of recognising visual objects regardless of whether they are photographed, painted, drawn, etc. It is a potentially significant yet under-researched problem. Emulating the remarkable human ability to recognise objects in an astonishingly wide variety of depictive forms is likely to advance both the foundations and the applications of Computer Vision. In this paper we benchmark classification, domain adaptation, and deep learning methods; demonstrating that none perform consistently well in the cross-depiction problem. Given the current interest in deep learning, the fact such methods exhibit the same behaviour as all but one other method: they show a significant fall in performance over inhomogeneous databases compared to their peak performance, which is always over data comprising photographs only. Rather, we find the methods that have strong models of spatial relations between parts tend to be more robust and therefore conclude that such information is important in modelling object classes regardless of appearance details.

cs.CV↗