Publications

Decomposed evaluations of geographic disparities in text-to-image models
Abhishek Sureddy
Dishant Padalia
Nandhinee Periyakaruppan
Oindrila Saha
Adina Williams
Adriana Romero
Megan Richards
Polina Kirichenko
Melissa Hall
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
doi.org
openreview.net
Economic evaluation of the effect of needle and syringe programs on skin, soft tissue, and vascular infections in people who inject drugs: a microsimulation modelling approach
Jihoon Lim
W. Alton Russell
Mariam El-Sheikh
David L. Buckeridge
Dimitra Panagiotoglou
Needle and syringe programs (NSP) are effective harm-reduction strategies against HIV and hepatitis C. Although skin, soft tissue, and vascu… (see more)lar infections (SSTVI) are the most common morbidities in people who inject drugs (PWID), the extent to which NSP are clinically and cost-effective in relation to SSTVI in PWID remains unclear. The objective of this study was to model the clinical- and cost-effectiveness of NSP with respect to treatment of SSTVI in PWID. We performed a model-based, economic evaluation comparing a scenario with NSP to a scenario without NSP. We developed a microsimulation model to generate two cohorts of 100,000 individuals corresponding to each NSP scenario and estimated quality-adjusted life-years (QALY) and cost (in 2022 Canadian dollars) over a 5-year time horizon (1.5% per annum for costs and outcomes). To assess the clinical effectiveness of NSP, we conducted survival analysis that accounted for the recurrent use of health care services for treating SSTVI and SSTVI mortality in the presence of competing risks. The incremental cost-effectiveness ratio associated with NSP was
2024-06-27
Harm Reduction Journal (published)
doi.org
Game On, Hate Off: A Study of Toxicity in Online Multiplayer Environments.
Zachary Yang
Nicolas Grenon-Godbout
Reihaneh Rabbany
The advent of online spaces, particularly social media platforms and video games, has brought forth a significant challenge: the detection a… (see more)nd mitigation of toxic and harmful speech. This issue is not only pervasive but also detrimental to the overall user experience. In this study, we leverage small language models to reliably detect toxicity, achieving an average precision of 0.95. Analyzing eight months of chat data from two Ubisoft games, we uncover patterns and trends in toxic behavior. The insights derived from our research will contribute to the development of healthier online communities and inform preventive measures against toxicity.
2024-06-27
Games: Research and Practice (published)
doi.org
In-Context Learning, Can It Break Safety?
Sophie Xhonneux
David Dobre
Michael Noukhovitch
Jian Tang
Gauthier Gidel
Dhanya Sridhar
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
openreview.net
openreview.net
Predicting the Population Risk of Suicide Using Routinely Collected Health Administrative Data in Quebec, Canada: Model-Based Synthetic Estimation Study
JianLi Wang
Fatemeh Gholi Zadeh Kharrat
Geneviève Gariépy
Christian Gagné
Jean-François Pelletier
Victoria Massamba
Pascale Lévesque
Mada Mohammed
Alain Lesage
2024-06-27
JMIR Public Health and Surveillance (published)
doi.org
A Randomized Controlled Simulation Trial of a Neonatal Resuscitation Digital Game Simulator for Labour and Delivery Room Staff
Christiane Bilodeau
Georg M. Schmölzer
Maria Cutumisu
2024-06-27
Children (published)
doi.org
Robust Knowledge Unlearning via Mechanistic Localizations
Phillip Huang Guo
Aaquib Syed
Abhay Sheshadri
Aidan Ewart
Gintare Karolina Dziugaite
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
openreview.net
openreview.net
Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
Rishika Bhagwatkar
Shravan Nayak
Reza Bayat
Alexis Roger
Daniel Z Kaplan
Pouya Bashivan
Irina Rish
Vision-Language Models (VLMs) have witnessed a surge in both research and real-world applications. However, as they becoming increasingly pr… (see more)evalent, ensuring their robustness against adversarial attacks is paramount. This work systematically investigates the impact of model design choices on the adversarial robustness of VLMs against image-based attacks. Additionally, we introduce novel, cost-effective approaches to enhance robustness through prompt formatting. By rephrasing questions and suggesting potential adversarial perturbations, we demonstrate substantial improvements in model robustness against strong image-based attacks such as Auto-PGD. Our findings provide important guidelines for developing more robust VLMs, particularly for deployment in safety-critical environments.
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
doi.org
openreview.net
A Context-Driven Approach for Co-Auditing Smart Contracts with The Support of GPT-4 code interpreter
Mohamed Salah Bouafif
Chen Zheng
Ilham Qasse
Ed Zulkoski
Mohammad Hamdaqa
Foutse Khomh
The surge in the adoption of smart contracts necessitates rigorous auditing to ensure their security and reliability. Manual auditing, altho… (see more)ugh comprehensive, is time-consuming and heavily reliant on the auditor's expertise. With the rise of Large Language Models (LLMs), there is growing interest in leveraging them to assist auditors in the auditing process (co-auditing). However, the effectiveness of LLMs in smart contract co-auditing is contingent upon the design of the input prompts, especially in terms of context description and code length. This paper introduces a novel context-driven prompting technique for smart contract co-auditing. Our approach employs three techniques for context scoping and augmentation, encompassing code scoping to chunk long code into self-contained code segments based on code inter-dependencies, assessment scoping to enhance context description based on the target assessment goal, thereby limiting the search space, and reporting scoping to force a specific format for the generated response. Through empirical evaluations on publicly available vulnerable contracts, our method demonstrated a detection rate of 96\% for vulnerable functions, outperforming the native prompting approach, which detected only 53\%. To assess the reliability of our prompting approach, manual analysis of the results was conducted by expert auditors from our partner, Quantstamp, a world-leading smart contract auditing company. The experts' analysis indicates that, in unlabeled datasets, our proposed approach enhances the proficiency of the GPT-4 code interpreter in detecting vulnerabilities.
2024-06-25
ArXiv (preprint)
doi.org
arxiv.org
Data harmonization for Advancing research on Personalized Rehabilitation Interventions for Patients with Traumatic Brain Injury and Stroke: A proof of concept
Dorra Rakia Allegue
Despoina Petsani
Nathalie Ponthon
Evdokimos Konstantinidis
Panagiotis Bamidis
Eva Kehayia
Audrey Durand
Sara Ahmed
Stroke and traumatic brain injury (TBI) are leading causes of morbidity and mortality, affecting survivors’ mobility and social participat… (see more)ion. Although personalized interventions could positively impact survivors' recovery, the effectiveness of such interventions remains unclear. Open-access data repositories can provide access to multiple shared data which could help uncover new evidence of effective interventions; however, harmonizing data between different studies requires many steps to make it possible given the various methods of data collection, intervention characteristics and population sociodemographic profile. This proof-of-concept study aimed to describe the steps and anchors that contributed to the development of guiding frameworks to harmonize data across different studies. Data were extracted from the Federal Interagency Traumatic Brain Injury Research (FITBIR) repository and stored on an online cloud platform. The outcome measures were mapped to mobility determinants using the International Classification of Functioning, Disability, and Health (ICF) and Webber framework. The intervention's effect was categorized according to the Minimal Clinically Important Difference (MCID)s of the measures administered. The study proposed a novel framework for intervention features, which aims to enhance our understanding of the mechanisms of action and potential impact of rehabilitation interventions. The framework classified interventions based on their nature, context, specific body systems, dosage, caregiver assistance, and behaviour change strategies. In conclusion, this study demonstrated the feasibility of harmonizing data extracted from different sources in the FITBIR repository. Leveraging existing open databases offers tremendous opportunities to advance research on personalized interventions for patients with TBI and stroke and inform decision-making during transitions.
2024-06-25
Petra (published)
doi.org
Learning to Design Data-structures: A Case Study of Nearest Neighbor Search
Omar Salemohamed
Vatsal Sharan
Shivam Garg
Laurent Charlin
Gregory Valiant
We propose a general framework for automating data-structure design and apply it to the problem of nearest neighbor search. Our model adapts… (see more) to the underlying data distribution and provides fine-grained control over query and space complexity, enabling the discovery of solutions tailored to problem-specific constraints. We are able to reverse-engineer learned algorithms in several settings. In 1D, the model discovers optimal distribution (in)dependent algorithms such as binary search and variants of interpolation search. In higher dimensions, the model learns solutions that resemble K-d trees in some regimes, while in others, have elements of locality-sensitive hashing.
2024-06-25
ICML.cc/2024/Workshop/Differentiable_Almost_Everything (published)
openreview.net
openreview.net
BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averaging
Zeinab Sherkatghanad
Moloud Abdar
Mohammadreza Bakhtyari
Vladimir Makarenkov
Test-time augmentation (TTA) is a well-known technique employed during the testing phase of computer vision tasks. It involves aggregating m… (see more)ultiple augmented versions of input data. Combining predictions using a simple average formulation is a common and straightforward approach after performing TTA. This paper introduces a novel framework for optimizing TTA, called BayTTA (Bayesian-based TTA), which is based on Bayesian Model Averaging (BMA). First, we generate a model list associated with different variations of the input data created through TTA. Then, we use BMA to combine model predictions weighted by their respective posterior probabilities. Such an approach allows one to take into account model uncertainty, and thus to enhance the predictive performance of the related machine learning or deep learning model. We evaluate the performance of BayTTA on various public data, including three medical image datasets comprising skin cancer, breast cancer, and chest X-ray images and two well-known gene editing datasets, CRISPOR and GUIDE-seq. Our experimental results indicate that BayTTA can be effectively integrated into state-of-the-art deep learning models used in medical image analysis as well as into some popular pre-trained CNN models such as VGG-16, MobileNetV2, DenseNet201, ResNet152V2, and InceptionRes-NetV2, leading to the enhancement in their accuracy and robustness performance.
2024-06-24
ArXiv (preprint)
doi.org
arxiv.org