Kevin Warren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Kevin Warren has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Kevin Butler
University of Florida, Gainesville, USA
4 shared publications - Patrick Traynor
University of Florida, Gainesville, Florida, USA
4 shared publications - Daniel Olszewski
University of Florida, Gainesville, FL, USA
3 shared publications - Allison Lu
University of Florida, Gainesville, FL, USA
2 shared publications - Anna Crowder
University of Florida, Gainesville, FL, USA
2 shared publications - Carrie Gates
Dalhousie University, Halifax, Nova Scotia, Canada
2 shared publications
Latest Publications
- Open Access
- 12 September 2025
- Published by Association for Computing Machinery (ACM) in Digital Threats: Research and Practice
- Vol. 6 (3) , 1-18
Every Breath You Don’t Take: Deepfake Speech Detection Using Breath
Deepfake speech represents a real and growing threat to systems and society. Many detectors have been created to aid in defense against speech deepfakes. While these detectors implement myriad methodologies, many rely on low-level fragments of the speech generation process. We hypothesize that breath, a higher-level part of speech, is a key component of natural speech and thus improper generation in deepfake speech is a performant discriminator. To evaluate this, we create a breath detector and leverage this against a custom dataset of online news article audio to discriminate between real/deepfake speech. Additionally, we make this custom dataset publicly available to facilitate comparison for future work. Applying our simple breath detector as a deepfake speech discriminator on in-the-wild samples allows for accurate classification (perfect 1.0 AUPRC and 0.0 EER on test data) across 33.6 hours of audio. We compare our model with the state-of-the-art SSL-wav2vec and Codecfake models and show that these complex deep learning model completely either fail to classify the same in-the-wild samples (0.72 AUPRC and 0.89 EER), or substantially lack in the computational and temporal performance compared to our methodology (37 seconds to predict a 1 minute sample with Codecfake vs. 0.3 seconds with our model).
- 12 September 2025
- Published by Association for Computing Machinery (ACM) in Digital Threats: Research and Practice
- Vol. 6 (3) , 1-18
Open AccessEvery Breath You Don’t Take: Deepfake Speech Detection Using Breath
Deepfake speech represents a real and growing threat to systems and society. Many detectors have been created to aid in defense against speech deepfakes. While these detectors implement myriad methodologies, many rely on low-level fragments of the speech generation process. We hypothesize that breath, a higher-level part of speech, is a key component of natural speech and thus improper generation in deepfake speech is a performant discriminator. To evaluate this, we create a breath detector and leverage this against a custom dataset of online news article audio to discriminate between real/deepfake speech. Additionally, we make this custom dataset publicly available to facilitate comparison for future work. Applying our simple breath detector as a deepfake speech discriminator on in-the-wild samples allows for accurate classification (perfect 1.0 AUPRC and 0.0 EER on test data) across 33.6 hours of audio. We compare our model with the state-of-the-art SSL-wav2vec and Codecfake models and show that these complex deep learning model completely either fail to classify the same in-the-wild samples (0.72 AUPRC and 0.89 EER), or substantially lack in the computational and temporal performance compared to our methodology (37 seconds to predict a 1 minute sample with Codecfake vs. 0.3 seconds with our model).
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 4197-4211
"I Had Sort of a Sense that I Was Always Being Watched...Since I Was": Examining Interpersonal Discomfort From Continuous Location-Sharing Applications
Continuous location sharing (CLS) applications are widely used for safety and social convenience. However, these applications have privacy concerns that can be used for control and harm. To understand user concerns, we performed the largest user study of CLS application usage performed to date, with 1500 of 3000 users indicating they use CLS applications and 896 of these users completing surveys. From survey responses, we conducted 23 interviews with participants who had uncomfortable experiences. With these interviews, we perform thematic analysis grounded by sociological frameworks of power dynamics and social exchange theory. We observe that CLS application users face discomfort related to three primary categories that build on each other: (1) overstepped boundaries, (2) continued discomfort, and (3) lifestyle-impacting behaviors. With this foundational understanding, we suggest features that aim to reduce relationship imbalances that CLS applications enable. Our resulting study demonstrates that CLS applications contribute to interpersonal discomfort, highlighting the need for design changes.
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 4197-4211
Open Access"I Had Sort of a Sense that I Was Always Being Watched...Since I Was": Examining Interpersonal Discomfort From Continuous Location-Sharing Applications
Continuous location sharing (CLS) applications are widely used for safety and social convenience. However, these applications have privacy concerns that can be used for control and harm. To understand user concerns, we performed the largest user study of CLS application usage performed to date, with 1500 of 3000 users indicating they use CLS applications and 896 of these users completing surveys. From survey responses, we conducted 23 interviews with participants who had uncomfortable experiences. With these interviews, we perform thematic analysis grounded by sociological frameworks of power dynamics and social exchange theory. We observe that CLS application users face discomfort related to three primary categories that build on each other: (1) overstepped boundaries, (2) continued discomfort, and (3) lifestyle-impacting behaviors. With this foundational understanding, we suggest features that aim to reduce relationship imbalances that CLS applications enable. Our resulting study demonstrates that CLS applications contribute to interpersonal discomfort, highlighting the need for design changes.
- Open Access
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 2696-2710
"Better Be Computer or I'm Dumb": A Large-Scale Evaluation of Humans as Audio Deepfake Detectors
- 2 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 2696-2710
Open Access"Better Be Computer or I'm Dumb": A Large-Scale Evaluation of Humans as Audio Deepfake Detectors
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 71 (4) , 535-541
Contribution of Secondary Alpha Particles to Soft Error Rates in Space Systems
The importance of including secondary particles in particle environments for SEE simulations is examined by comparing total error rates with and without secondary alpha particles as a result of target fragmentation. Previous experimental single event tests have demonstrated importance of short-range, high-LET secondary particles, produced by target fragmentation near to device. However, current error rate prediction workflows, based on tools such as CREME96 and SPENVIS, do not account for these secondary particles from target fragmentation. Reevaluating those practices shows that the impact of secondary alpha particles on total error rates is negligible for the environments, devices, and aluminum shielding explored. To compare the broader issue of nuclear reactions in overlaying materials, energy deposition simulations were done in MRED, which indicate that the composition and sequence of overlying materials need to be considered with regards to secondary particle production.
- 7 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 71 (4) , 535-541
Contribution of Secondary Alpha Particles to Soft Error Rates in Space Systems
The importance of including secondary particles in particle environments for SEE simulations is examined by comparing total error rates with and without secondary alpha particles as a result of target fragmentation. Previous experimental single event tests have demonstrated importance of short-range, high-LET secondary particles, produced by target fragmentation near to device. However, current error rate prediction workflows, based on tools such as CREME96 and SPENVIS, do not account for these secondary particles from target fragmentation. Reevaluating those practices shows that the impact of secondary alpha particles on total error rates is negligible for the environments, devices, and aluminum shielding explored. To compare the broader issue of nuclear reactions in overlaying materials, energy deposition simulations were done in MRED, which indicate that the composition and sequence of overlying materials need to be considered with regards to secondary particle production.
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 3433-3459
"Get in Researchers; We're Measuring Reproducibility": A Reproducibility Study of Machine Learning Papers in Tier 1 Security Conferences
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 3433-3459
Open Access"Get in Researchers; We're Measuring Reproducibility": A Reproducibility Study of Machine Learning Papers in Tier 1 Security Conferences