Publications

Black-Box Access is Insufficient for Rigorous AI Audits
Stephen Casper
Carson Ezell
Charlotte Siegmann
Noam Kolt
Taylor Lynn Curtis
Benjamin Bucknall
Andreas A. Haupt
Kevin Wei
J'er'emy Scheurer
Marius Hobbhahn
Lee Sharkey
Satyapriya Krishna
Marvin von Hagen
Silas Alberti
Alan Chan
Qinyi Sun
Michael Gerovitch
David Bau
Max Tegmark
David Scott Krueger … (see 1 more)
Dylan Hadfield-Menell
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depe… (see more)nds on the degree of system access granted to auditors. Recent audits of state-of-the-art AI systems have primarily relied on black-box access, in which auditors can only query the system and observe its outputs. However, white-box access to the system's inner workings (e.g., weights, activations, gradients) allows an auditor to perform stronger attacks, more thoroughly interpret models, and conduct fine-tuning. Meanwhile, outside-the-box access to its training and deployment information (e.g., methodology, code, documentation, hyperparameters, data, deployment details, findings from internal evaluations) allows for auditors to scrutinize the development process and design more targeted evaluations. In this paper, we examine the limitations of black-box audits and the advantages of white- and outside-the-box audits. We also discuss technical, physical, and legal safeguards for performing these audits with minimal security risks. Given that different forms of access can lead to very different levels of evaluation, we conclude that (1) transparency regarding the access and methods used by auditors is necessary to properly interpret audit results, and (2) white- and outside-the-box access allow for substantially more scrutiny than black-box access alone.
2024-01-25
ArXiv (preprint)
doi.org
arxiv.org
Human-Centered AI
Catherine Régis
Jean-Louis Denis
Maria Luciana Axente
Atsuo Kishimoto
2024-01-25
(published)
doi.org
Neighbor-Aware Calibration of Segmentation Networks with Penalty-Based Constraints
Balamurali Murugesan
Sukesh Adiga Vasudeva
Bingyuan Liu
Hervé Lombaert
Ismail Ben Ayed
Jose Dolz
Ensuring reliable confidence scores from deep neural networks is of paramount significance in critical decision-making systems, particularly… (see more) in real-world domains such as healthcare. Recent literature on calibrating deep segmentation networks has resulted in substantial progress. Nevertheless, these approaches are strongly inspired by the advancements in classification tasks, and thus their uncertainty is usually modeled by leveraging the information of individual pixels, disregarding the local structure of the object of interest. Indeed, only the recent Spatially Varying Label Smoothing (SVLS) approach considers pixel spatial relationships across classes, by softening the pixel label assignments with a discrete spatial Gaussian kernel. In this work, we first present a constrained optimization perspective of SVLS and demonstrate that it enforces an implicit constraint on soft class proportions of surrounding pixels. Furthermore, our analysis shows that SVLS lacks a mechanism to balance the contribution of the constraint with the primary objective, potentially hindering the optimization process. Based on these observations, we propose NACL (Neighbor Aware CaLibration), a principled and simple solution based on equality constraints on the logit values, which enables to control explicitly both the enforced constraint and the weight of the penalty, offering more flexibility. Comprehensive experiments on a wide variety of well-known segmentation benchmarks demonstrate the superior calibration performance of the proposed approach, without affecting its discriminative power. Furthermore, ablation studies empirically show the model agnostic nature of our approach, which can be used to train a wide span of deep segmentation networks.
2024-01-25
ArXiv (preprint)
doi.org
arxiv.org
Probabilistic Mobility Load Balancing for Multi-band 5G and Beyond Networks
Saria Al Laham
Di Wu
Ekram Hossain
Xue (Steve) Liu
Gregory Dudek
2024-01-24
ArXiv (preprint)
doi.org
arxiv.org
Beyond Predictive Algorithms in Child Welfare
Erina Seh-Young Moon
Erin Moon
Devansh Saxena
Tegan Maharaj
Shion Guha
2024-01-23
graphicsinterface.org/Graphics_Interface/2024/Conference (published)
doi.org
openreview.net
Visibility into AI Agents
Alan Chan
Carson Ezell
Max Kaufmann
Kevin Wei
Lewis Hammond
Herbie Bradley
Emma Bluemke
Nitarshan Rajkumar
David Scott Krueger
Noam Kolt
Lennart Heim
Markus Anderljung
2024-01-23
ArXiv (preprint)
doi.org
arxiv.org
Connectome-based reservoir computing with the conn2res toolbox
Laura E. Suárez
Agoston Mihalik
Filip Milisav
Kenji Marshall
Mingze Li
Petra E. Vértes
Guillaume Lajoie
Bratislav Mišić
2024-01-22
Nature Communications (published)
doi.org
RapidBrachyTG43: A Geant4‐based TG‐43 parameter and dose calculation module for brachytherapy dosimetry
Jonathan Kalinowski
Shirin A. Enger
2024-01-22
Medical Physics (published)
doi.org
Transnational conservation to anticipate future plant shifts in Europe
Yohann Chauvier-Mendes
Laura J. Pollock
Peter H. Verburg
Dirk N. Karger
Loïc Pellissier
Sébastien Lavergne
Niklaus E. Zimmermann
Wilfried Thuiller
2024-01-22
Nature Ecology & Evolution (published)
doi.org
Gaining Biological Insights through Supervised Data Visualization
Jake S. Rhodes
Adrien Aumon
Sacha Morin
Marc Girard
Catherine Larochelle
Boaz Lahav
Elsa Brunet-Ratnasingham
Amélie Pagliuzza
Lorie Marchitto
Wei Zhang
Adele Cutler
F. Grand'Maison
Anhong Zhou
Andrés Finzi
Nicolas Chomont
Daniel E. Kaufmann
Stephanie Zandee
Alexandre Prat
Guy Wolf
Kevin R. Moon
Dimensionality reduction-based data visualization is pivotal in comprehending complex biological data. The most common methods, such as PHAT… (see more)E, t-SNE, and UMAP, are unsupervised and therefore reflect the dominant structure in the data, which may be independent of expert-provided labels. Here we introduce a supervised data visualization method called RF-PHATE, which integrates expert knowledge for further exploration of the data. RF-PHATE leverages random forests to capture intricate featurelabel relationships. Extracting information from the forest, RF-PHATE generates low-dimensional visualizations that highlight relevant data relationships while disregarding extraneous features. This approach scales to large datasets and applies to classification and regression. We illustrate RF-PHATE’s prowess through three case studies. In a multiple sclerosis study using longitudinal clinical and imaging data, RF-PHATE unveils a sub-group of patients with non-benign relapsingremitting Multiple Sclerosis, demonstrating its aptitude for time-series data. In the context of Raman spectral data, RF-PHATE effectively showcases the impact of antioxidants on diesel exhaust-exposed lung cells, highlighting its proficiency in noisy environments. Furthermore, RF-PHATE aligns established geometric structures with COVID-19 patient outcomes, enriching interpretability in a hierarchical manner. RF-PHATE bridges expert insights and visualizations, promising knowledge generation. Its adaptability, scalability, and noise tolerance underscore its potential for widespread adoption.
2024-01-21
bioRxiv (preprint)
doi.org
EMA-Net: Efficient Multitask Affinity Learning for Dense Scene Predictions
Dimitrios Sinodinos
Narges Armanfard
2024-01-20
ArXiv (preprint)
doi.org
arxiv.org
PhotoBot: Reference-Guided Interactive Photography via Natural Language
Oliver Limoyo
Jimmy Li
Dmitriy Rivkin
Jonathan Kelly
Gregory Dudek
We introduce PhotoBot, a framework for fully automated photo acquisition based on an interplay between high-level human language guidance an… (see more)d a robot photographer. We propose to communicate photography suggestions to the user via reference images that are selected from a curated gallery. We leverage a visual language model (VLM) and an object detector to characterize the reference images via textual descriptions and then use a large language model (LLM) to retrieve relevant reference images based on a user's language query through text-based reasoning. To correspond the reference image and the observed scene, we exploit pre-trained features from a vision transformer capable of capturing semantic similarity across marked appearance variations. Using these features, we compute pose adjustments for an RGB-D camera by solving a perspective-n-point (PnP) problem. We demonstrate our approach using a manipulator equipped with a wrist camera. Our user studies show that photos taken by PhotoBot are often more aesthetically pleasing than those taken by users themselves, as measured by human feedback. We also show that PhotoBot can generalize to other reference sources such as paintings.
2024-01-19
ArXiv (preprint)
doi.org
arxiv.org