Thomas Hartvigsen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Thomas Hartvigsen has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Dongliang Guo
University of Virginia, Charlottesville, VA, USA
2 shared publications - Marzyeh Ghassemi
Massachusetts Institute of Technology, Cambridge, USA
2 shared publications Adrien Boch
Evidation Health Inc, San Mateo, USA
1 shared publicationAnna Goldenberg
Department of Computer Science, University of Toronto, Toronto, Canada
1 shared publication- Brynne Archer Sullivan
Division of Neonatology, Department of Pediatrics, University of Virginia School of Medicine, Charlottesville, USA
1 shared publication - Elizabeth Bondi-Kelly
University of Michigan, Ann Arbor, MI, USA
1 shared publication
Latest Publications
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1216-1227
Instruction-based Time Series Editing
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1216-1227
Open AccessInstruction-based Time Series Editing
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 750-760
Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack (i.e., backdoor attack) can manipulate the behavior of machine learning models through contaminating their training dataset, posing significant threat in the real-world application of large pre-trained model, especially for those customized models. Therefore, addressing the unique challenges for exploring vulnerability of pre-trained models is of paramount importance. Through empirical studies on the capability for performing backdoor attack in large pre-trained models (e.g., ViT), we find the following unique challenges of attacking large pre-trained models: 1) the inability to manipulate or even access large training datasets, and 2) the substantial computational resources required for training or fine-tuning these models. To address these challenges, we establish new standards for an effective and feasible backdoor attack in the context of large pre-trained models. In line with these standards, we introduce our EDT model, an Efficient, Data-free, Training-free backdoor attack method. Inspired by model editing techniques, EDT injects an editing-based lightweight codebook into the backdoor of large pre-trained models, which replaces the embedding of the poisoned image with the target image without poisoning the training dataset or training the victim model. Our experiments, conducted across various pre-trained models such as ViT, CLIP, BLIP, and stable diffusion, and on downstream tasks including image classification, image captioning, and image generation, demonstrate the effectiveness of our method. Our code is available at https://github.com/donglgcn/Editing/
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 750-760
Open AccessBackdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing
Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack (i.e., backdoor attack) can manipulate the behavior of machine learning models through contaminating their training dataset, posing significant threat in the real-world application of large pre-trained model, especially for those customized models. Therefore, addressing the unique challenges for exploring vulnerability of pre-trained models is of paramount importance. Through empirical studies on the capability for performing backdoor attack in large pre-trained models (e.g., ViT), we find the following unique challenges of attacking large pre-trained models: 1) the inability to manipulate or even access large training datasets, and 2) the substantial computational resources required for training or fine-tuning these models. To address these challenges, we establish new standards for an effective and feasible backdoor attack in the context of large pre-trained models. In line with these standards, we introduce our EDT model, an Efficient, Data-free, Training-free backdoor attack method. Inspired by model editing techniques, EDT injects an editing-based lightweight codebook into the backdoor of large pre-trained models, which replaces the embedding of the poisoned image with the target image without poisoning the training dataset or training the victim model. Our experiments, conducted across various pre-trained models such as ViT, CLIP, BLIP, and stable diffusion, and on downstream tasks including image classification, image captioning, and image generation, demonstrate the effectiveness of our method. Our code is available at https://github.com/donglgcn/Editing/
- Open Access
- 20 December 2023
- Published by Springer Nature in npj Digital Medicine
- Vol. 6 (1) , 1-9
Dissecting the heterogeneity of “in the wild” stress from multimodal sensor data
Stress is associated with numerous chronic health conditions, both mental and physical. However, the heterogeneity of these associations at the individual level is poorly understood. While data generated from individuals in their day-to-day lives “in the wild” may best represent the heterogeneity of stress, gathering these data and separating signals from noise is challenging. In this work, we report findings from a major data collection effort using Digital Health Technologies (DHTs) and frontline healthcare workers. We provide insights into stress “in the wild”, by using robust methods for its identification from multimodal data and quantifying its heterogeneity. Here we analyze data from the Stress and Recovery in Frontline COVID-19 Workers study following 365 frontline healthcare workers for 4–6 months using wearable devices and smartphone app-based measures. Causal discovery is used to learn how the causal structure governing an individual’s self-reported symptoms and physiological features from DHTs differs between non-stress and potential stress states. Our methods uncover robust representations of potential stress states across a population of frontline healthcare workers. These representations reveal high levels of inter- and intra-individual heterogeneity in stress. We leverage multiple stress definitions that span different modalities (from subjective to physiological) to obtain a comprehensive view of stress, as these differing definitions rarely align in time. We show that these different stress definitions can be robustly represented as changes in the underlying causal structure on and off stress for individuals. This study is an important step toward better understanding potential underlying processes generating stress in individuals.
- 20 December 2023
- Published by Springer Nature in npj Digital Medicine
- Vol. 6 (1) , 1-9
Open AccessDissecting the heterogeneity of “in the wild” stress from multimodal sensor data
Stress is associated with numerous chronic health conditions, both mental and physical. However, the heterogeneity of these associations at the individual level is poorly understood. While data generated from individuals in their day-to-day lives “in the wild” may best represent the heterogeneity of stress, gathering these data and separating signals from noise is challenging. In this work, we report findings from a major data collection effort using Digital Health Technologies (DHTs) and frontline healthcare workers. We provide insights into stress “in the wild”, by using robust methods for its identification from multimodal data and quantifying its heterogeneity. Here we analyze data from the Stress and Recovery in Frontline COVID-19 Workers study following 365 frontline healthcare workers for 4–6 months using wearable devices and smartphone app-based measures. Causal discovery is used to learn how the causal structure governing an individual’s self-reported symptoms and physiological features from DHTs differs between non-stress and potential stress states. Our methods uncover robust representations of potential stress states across a population of frontline healthcare workers. These representations reveal high levels of inter- and intra-individual heterogeneity in stress. We leverage multiple stress definitions that span different modalities (from subjective to physiological) to obtain a comprehensive view of stress, as these differing definitions rarely align in time. We show that these different stress definitions can be robustly represented as changes in the underlying causal structure on and off stress for individuals. This study is an important step toward better understanding potential underlying processes generating stress in individuals.
- Open Access
- 30 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Taking Off with AI: Lessons from Aviation for Healthcare
- 30 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-14
Open AccessTaking Off with AI: Lessons from Aviation for Healthcare
- Open Access
- 26 February 2023
- Published by PubPub
- No. Winter 202
Algorithmic Fairness in Chest X-ray Diagnosis: A Case Study
Machine learning models are being increasingly deployed in real-world clinical environments. However, these models often exhibit disparate performance between population groups, potentially leading to inequitable and discriminatory predictions. In this case study, we use several distinct concepts of algorithmic fairness to analyze a deep learning model that predicts from their chest X-ray whether someone has a disease. After observing disparities in the false positive rate and false negative rate between groups from several protected classes, we apply algorithmic fairness methods to remove such disparities. However, we find that such algorithmic interventions can have serious unintended consequences. Finally, we question what the appropriate definition of fairness is in the clinical context, and advocate for an investigation of bias in the data whenever possible, as opposed to blindly applying algorithmic interventions.
- 26 February 2023
- Published by PubPub
- No. Winter 202
Open AccessAlgorithmic Fairness in Chest X-ray Diagnosis: A Case Study
Machine learning models are being increasingly deployed in real-world clinical environments. However, these models often exhibit disparate performance between population groups, potentially leading to inequitable and discriminatory predictions. In this case study, we use several distinct concepts of algorithmic fairness to analyze a deep learning model that predicts from their chest X-ray whether someone has a disease. After observing disparities in the false positive rate and false negative rate between groups from several protected classes, we apply algorithmic fairness methods to remove such disparities. However, we find that such algorithmic interventions can have serious unintended consequences. Finally, we question what the appropriate definition of fairness is in the clinical context, and advocate for an investigation of bias in the data whenever possible, as opposed to blindly applying algorithmic interventions.