Preston K. Robinette
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Preston K. Robinette has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Taylor Thomas Johnson
Vanderbilt University
8 shared publications - Diego Manzanas Lopez
Vanderbilt University
4 shared publications Daniel Moyer
Vanderbilt University
3 shared publications- Nathaniel Hamilton
Vanderbilt University
3 shared publications Taylor T. Johnson
Vanderbilt University
3 shared publicationsHanchen D. Wang
Vanderbilt University
2 shared publications
Latest Publications
- Open Access
- 8 July 2026
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 86
Towards Verified and Targeted Explanations through Formal Methods
As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations of model behavior that are not only interpretable but also trustworthy with formal guarantees. Existing XAI methods fall short of this requirement: heuristic attribution techniques (e.g., LIME, Integrated Gradients) highlight influential features for individual predictions but offer no mathematical guarantees about decision boundaries, while formal explanation methods verify robustness properties yet remain untargeted, analyzing the nearest boundary regardless of whether it represents a critical risk. In safety-critical systems, however, not all misclassifications carry equal consequences; confusing a “Stop” sign for a “60 kph” sign is far more dangerous than confusing it with a “No Passing” sign. Practitioners therefore lack a principled way to answer a fundamental safety question: how resilient is a model’s classification against a specific, high-risk alternative? We introduce ViTaX (Verified and Targeted Explanations), a formal XAI framework that addresses this gap by generating targeted semifactual explanations with mathematical guarantees. For a given input (class y) and a user-specified critical alternative (class t), ViTaX performs two key steps: (1) it identifies the minimal feature subset most sensitive to the y → t transition using class-specific sensitivity heuristics, and (2) it applies formal reachability analysis to guarantee that perturbing these features by ε is insufficient to flip the classification to t. This guarantee constitutes a verified semifactual: “even if these critical features change by ε classification y persists against t." We formalize this reasoning through Targeted ε-Robustness, a formal property that certifies whether an identified feature subset remains robust under perturbation toward a specific target class. By unifying semifactual explanations, class-specific targeting, and formal verification, ViTaX is the first method to provide formally guaranteed explanations of a model’s resilience against specific, user-identified alternatives. Our evaluations on image classification (MNIST, GTSRB, EMNIST) and regression (TaxiNet) demonstrate that ViTaX achieves significantly higher fidelity (e.g., over 30% improvement) and minimal explanation cardinality compared to existing methods. These results establish ViTaX as a scalable and trustworthy foundation for verifiable, targeted XAI.
- 8 July 2026
- Published by AI Access Foundation in Journal of Artificial Intelligence Research
- Vol. 86
Open AccessTowards Verified and Targeted Explanations through Formal Methods
As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations of model behavior that are not only interpretable but also trustworthy with formal guarantees. Existing XAI methods fall short of this requirement: heuristic attribution techniques (e.g., LIME, Integrated Gradients) highlight influential features for individual predictions but offer no mathematical guarantees about decision boundaries, while formal explanation methods verify robustness properties yet remain untargeted, analyzing the nearest boundary regardless of whether it represents a critical risk. In safety-critical systems, however, not all misclassifications carry equal consequences; confusing a “Stop” sign for a “60 kph” sign is far more dangerous than confusing it with a “No Passing” sign. Practitioners therefore lack a principled way to answer a fundamental safety question: how resilient is a model’s classification against a specific, high-risk alternative? We introduce ViTaX (Verified and Targeted Explanations), a formal XAI framework that addresses this gap by generating targeted semifactual explanations with mathematical guarantees. For a given input (class y) and a user-specified critical alternative (class t), ViTaX performs two key steps: (1) it identifies the minimal feature subset most sensitive to the y → t transition using class-specific sensitivity heuristics, and (2) it applies formal reachability analysis to guarantee that perturbing these features by ε is insufficient to flip the classification to t. This guarantee constitutes a verified semifactual: “even if these critical features change by ε classification y persists against t." We formalize this reasoning through Targeted ε-Robustness, a formal property that certifies whether an identified feature subset remains robust under perturbation toward a specific target class. By unifying semifactual explanations, class-specific targeting, and formal verification, ViTaX is the first method to provide formally guaranteed explanations of a model’s resilience against specific, user-identified alternatives. Our evaluations on image classification (MNIST, GTSRB, EMNIST) and regression (TaxiNet) demonstrate that ViTaX achieves significantly higher fidelity (e.g., over 30% improvement) and minimal explanation cardinality compared to existing methods. These results establish ViTaX as a scalable and trustworthy foundation for verifiable, targeted XAI.
- 13 October 2025
- Published by Springer Nature
- p. 346-365
Trigger-Based Fragile Model Watermarking for Image Transformation Networks
- 13 October 2025
- Published by Springer Nature
- p. 346-365
Trigger-Based Fragile Model Watermarking for Image Transformation Networks
- Open Access
Blind Visible Watermark Removal with Morphological Dilation
Visible watermarks pose significant challenges for image restoration techniques, especially when the target background is unknown. Toward this end, we present MorphoMod, a novel method for automated visible watermark removal that operates in a blind setting -- without requiring target images. Unlike existing methods, MorphoMod effectively removes opaque and transparent watermarks while preserving semantic content, making it well-suited for real-world applications. Evaluations on benchmark datasets, including the Colored Large-scale Watermark Dataset (CLWD), LOGO-series, and the newly introduced Alpha1 datasets, demonstrate that MorphoMod achieves up to a 50.8% improvement in watermark removal effectiveness compared to state-of-the-art methods. Ablation studies highlight the impact of prompts used for inpainting, pre-removal filling strategies, and inpainting model performance on watermark removal. Additionally, a case study on steganographic disorientation reveals broader applications for watermark removal in disrupting high-level hidden messages. MorphoMod offers a robust, adaptable solution for watermark removal and opens avenues for further advancements in image restoration and adversarial manipulation.
Open AccessBlind Visible Watermark Removal with Morphological Dilation
Visible watermarks pose significant challenges for image restoration techniques, especially when the target background is unknown. Toward this end, we present MorphoMod, a novel method for automated visible watermark removal that operates in a blind setting -- without requiring target images. Unlike existing methods, MorphoMod effectively removes opaque and transparent watermarks while preserving semantic content, making it well-suited for real-world applications. Evaluations on benchmark datasets, including the Colored Large-scale Watermark Dataset (CLWD), LOGO-series, and the newly introduced Alpha1 datasets, demonstrate that MorphoMod achieves up to a 50.8% improvement in watermark removal effectiveness compared to state-of-the-art methods. Ablation studies highlight the impact of prompts used for inpainting, pre-removal filling strategies, and inpainting model performance on watermark removal. Additionally, a case study on steganographic disorientation reveals broader applications for watermark removal in disrupting high-level hidden messages. MorphoMod offers a robust, adaptable solution for watermark removal and opens avenues for further advancements in image restoration and adversarial manipulation.
- Open Access
- 14 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 36-44
FairNNV: The Neural Network Verification Tool For Certifying Fairness
Ensuring fairness in machine learning (ML) is vital, especially as these models are increasingly used in socially critical financial decision-making processes such as credit scoring, loan approvals, and fraud detection. Fairness verification aims to provide formal guarantees of fairness in ML models. In this work, we introduce FairNNV, a tool that leverages the Neural Network Verification (NNV) framework to verify individual and counterfactual fairness using reachability analysis techniques. FairNNV introduces the Verified Fairness (VF) score to quantify fairness. Additionally, we compare the verification process of models before and after applying adversarial debiasing techniques to assess the impact of bias mitigation. We demonstrate FairNNV’s effectiveness on several fairness benchmark datasets, including Adult Census, German Credit, and Bank Marketing, with a focused analysis on the impact of adversarial debiasing on Adult Census classifiers. Experimental results show differences between empirical fairness improvements using adversarial debiasing and fairness verification scores with FairNNV, indicating a need for integrating formal verification into the evaluation process to guide model selections when assessing fairness.
- 14 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 36-44
Open AccessFairNNV: The Neural Network Verification Tool For Certifying Fairness
Ensuring fairness in machine learning (ML) is vital, especially as these models are increasingly used in socially critical financial decision-making processes such as credit scoring, loan approvals, and fraud detection. Fairness verification aims to provide formal guarantees of fairness in ML models. In this work, we introduce FairNNV, a tool that leverages the Neural Network Verification (NNV) framework to verify individual and counterfactual fairness using reachability analysis techniques. FairNNV introduces the Verified Fairness (VF) score to quantify fairness. Additionally, we compare the verification process of models before and after applying adversarial debiasing techniques to assess the impact of bias mitigation. We demonstrate FairNNV’s effectiveness on several fairness benchmark datasets, including Adult Census, German Credit, and Bank Marketing, with a focused analysis on the impact of adversarial debiasing on Adult Census classifiers. Experimental results show differences between empirical fairness improvements using adversarial debiasing and fairness verification scores with FairNNV, indicating a need for integrating formal verification into the evaluation process to guide model selections when assessing fairness.
- Open Access
- 16 October 2024
- Published by IOS Press
- p. 778-785
Sanitizing Hidden Information with Diffusion Models
Information hiding is the process of embedding data within another form of data, often to conceal its existence or prevent unauthorized access. This process is commonly used in various forms of secure communications (steganography) that can be used by bad actors to propagate malware, exfiltrate victim data, and discreetly communicate. Recent work has utilized deep neural networks to remove this hidden information in a defense mechanism known as sanitization. Previous deep learning works, however, are unable to scale efficiently beyond the MNIST dataset. In this work, we present a novel sanitization method called DM-SUDS that utilizes a diffusion model framework to sanitize/remove hidden information from image-into-image universal and dependent steganography from CIFAR-10 and ImageNet datasets. We evaluate DM-SUDS against three different baselines using MSE, PSNR, SSIM, and NCC metrics and provide further detailed analysis through an ablation study. DM-SUDS outperforms all three baselines and significantly improves image preservation MSE by 50.44%, PSNR by 12.69%, SSIM by 11.49%, and NCC by 3.26% compared to previous deep learning approaches. Additionally, we introduce a novel evaluation specification that considers the successful removal of hidden information (safety) as well as the resulting quality of the sanitized image (utility). We further demonstrate the versatility of this method with an application in an audio case study, demonstrating its broad applicability to additional domains.
- 16 October 2024
- Published by IOS Press
- p. 778-785
Open AccessSanitizing Hidden Information with Diffusion Models
Information hiding is the process of embedding data within another form of data, often to conceal its existence or prevent unauthorized access. This process is commonly used in various forms of secure communications (steganography) that can be used by bad actors to propagate malware, exfiltrate victim data, and discreetly communicate. Recent work has utilized deep neural networks to remove this hidden information in a defense mechanism known as sanitization. Previous deep learning works, however, are unable to scale efficiently beyond the MNIST dataset. In this work, we present a novel sanitization method called DM-SUDS that utilizes a diffusion model framework to sanitize/remove hidden information from image-into-image universal and dependent steganography from CIFAR-10 and ImageNet datasets. We evaluate DM-SUDS against three different baselines using MSE, PSNR, SSIM, and NCC metrics and provide further detailed analysis through an ablation study. DM-SUDS outperforms all three baselines and significantly improves image preservation MSE by 50.44%, PSNR by 12.69%, SSIM by 11.49%, and NCC by 3.26% compared to previous deep learning approaches. Additionally, we introduce a novel evaluation specification that considers the successful removal of hidden information (safety) as well as the resulting quality of the sanitized image (utility). We further demonstrate the versatility of this method with an application in an audio case study, demonstrating its broad applicability to additional domains.
- Open Access
Trigger-Based Fragile Model Watermarking for Image Transformation Networks
In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering. This fragile process can be used to ensure the integrity and source of watermarked objects. While fragile watermarking for model integrity has been studied in classification models, image transformation/generation models have yet to be explored. We introduce a novel, trigger-based fragile model watermarking system for image transformation/generation networks that takes advantage of properties inherent to image outputs. For example, manifesting watermarks as specific visual patterns, styles, or anomalies in the generated content when particular trigger inputs are used. Our approach, distinct from robust watermarking, effectively verifies the model's source and integrity across various datasets and attacks, outperforming baselines by 94%. We conduct additional experiments to analyze the security of this approach, the flexibility of the trigger and resulting watermark, and the sensitivity of the watermarking loss on performance. We also demonstrate the applicability of this approach on two different tasks (1 immediate task and 1 downstream task). This is the first work to consider fragile model watermarking for image transformation/generation networks.
Open AccessTrigger-Based Fragile Model Watermarking for Image Transformation Networks
In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering. This fragile process can be used to ensure the integrity and source of watermarked objects. While fragile watermarking for model integrity has been studied in classification models, image transformation/generation models have yet to be explored. We introduce a novel, trigger-based fragile model watermarking system for image transformation/generation networks that takes advantage of properties inherent to image outputs. For example, manifesting watermarks as specific visual patterns, styles, or anomalies in the generated content when particular trigger inputs are used. Our approach, distinct from robust watermarking, effectively verifies the model's source and integrity across various datasets and attacks, outperforming baselines by 94%. We conduct additional experiments to analyze the security of this approach, the flexibility of the trigger and resulting watermark, and the sensitivity of the watermarking loss on performance. We also demonstrate the applicability of this approach on two different tasks (1 immediate task and 1 downstream task). This is the first work to consider fragile model watermarking for image transformation/generation networks.
- Open Access
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 127-137
Case Study: Neural Network Malware Detection Verification for Feature and Image Datasets
Malware, or software designed with harmful intent, is an ever-evolving threat that can have drastic effects on both individuals and institutions. Neural network malware classification systems are key tools for combating these threats but are vulnerable to adversarial machine learning attacks. These attacks perturb input data to cause misclassification, bypassing protective systems. Existing defenses often rely on enhancing the training process, thereby increasing the model's robustness to these perturbations, which is quantified using verification. While training improvements are necessary, we propose focusing on the verification process used to evaluate improvements to training. As such, we present a case study that evaluates a novel verification domain that will help to ensure tangible safeguards against adversaries and provide a more reliable means of evaluating the robustness and effectiveness of anti-malware systems. To do so, we describe malware classification and two types of common malware datasets (feature and image datasets), demonstrate the certified robustness accuracy of malware classifiers using the Neural Network Verification (NNV) and Neural Network Enumeration (nnenum) tools1, and outline the challenges and future considerations necessary for the improvement and refinement of the verification of malware classification. By evaluating this novel domain as a case study, we hope to increase its visibility, encourage further research and scrutiny, and ultimately enhance the resilience of digital systems against malicious attacks.
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 127-137
Open AccessCase Study: Neural Network Malware Detection Verification for Feature and Image Datasets
Malware, or software designed with harmful intent, is an ever-evolving threat that can have drastic effects on both individuals and institutions. Neural network malware classification systems are key tools for combating these threats but are vulnerable to adversarial machine learning attacks. These attacks perturb input data to cause misclassification, bypassing protective systems. Existing defenses often rely on enhancing the training process, thereby increasing the model's robustness to these perturbations, which is quantified using verification. While training improvements are necessary, we propose focusing on the verification process used to evaluate improvements to training. As such, we present a case study that evaluates a novel verification domain that will help to ensure tangible safeguards against adversaries and provide a more reliable means of evaluating the robustness and effectiveness of anti-malware systems. To do so, we describe malware classification and two types of common malware datasets (feature and image datasets), demonstrate the certified robustness accuracy of malware classifiers using the Neural Network Verification (NNV) and Neural Network Enumeration (nnenum) tools1, and outline the challenges and future considerations necessary for the improvement and refinement of the verification of malware classification. By evaluating this novel domain as a case study, we hope to increase its visibility, encourage further research and scrutiny, and ultimately enhance the resilience of digital systems against malicious attacks.
- 14 December 2023
- Published by Springer Nature
- p. 291-298
Benchmark: Neural Network Malware Classification
- 14 December 2023
- Published by Springer Nature
- p. 291-298
Benchmark: Neural Network Malware Classification
- Open Access
- 28 September 2023
- Published by IOS Press
- p. 1978-1985
SUDS: Sanitizing Universal and Dependent Steganography
Steganography, or hiding messages in plain sight, is a form of information hiding that is most commonly used for covert communication. As modern steganographic mediums include images, text, audio, and video, this communication method is being increasingly used by bad actors to propagate malware, exfiltrate data, and discreetly communicate. Current protection mechanisms rely upon steganalysis, or the detection of steganography, but these approaches are dependent upon prior knowledge, such as steganographic signatures from publicly available tools and statistical knowledge about known hiding methods. These dependencies render steganalysis useless against new or unique hiding methods, which are becoming increasingly common with the application of deep learning models. To mitigate the shortcomings of steganalysis, this work focuses on a deep learning sanitization technique called SUDS that is not reliant upon knowledge of steganographic hiding techniques and is able to sanitize universal and dependent steganography. SUDS is tested using least significant bit method (LSB), dependent deep hiding (DDH), and universal deep hiding (UDH). We demonstrate the capabilities and limitations of SUDS by answering five research questions, including baseline comparisons and an ablation study. Additionally, we apply SUDS to a real-world scenario, where it is able to increase the resistance of a poisoned classifier against attacks by 1375%.
- 28 September 2023
- Published by IOS Press
- p. 1978-1985
Open AccessSUDS: Sanitizing Universal and Dependent Steganography
Steganography, or hiding messages in plain sight, is a form of information hiding that is most commonly used for covert communication. As modern steganographic mediums include images, text, audio, and video, this communication method is being increasingly used by bad actors to propagate malware, exfiltrate data, and discreetly communicate. Current protection mechanisms rely upon steganalysis, or the detection of steganography, but these approaches are dependent upon prior knowledge, such as steganographic signatures from publicly available tools and statistical knowledge about known hiding methods. These dependencies render steganalysis useless against new or unique hiding methods, which are becoming increasingly common with the application of deep learning models. To mitigate the shortcomings of steganalysis, this work focuses on a deep learning sanitization technique called SUDS that is not reliant upon knowledge of steganographic hiding techniques and is able to sanitize universal and dependent steganography. SUDS is tested using least significant bit method (LSB), dependent deep hiding (DDH), and universal deep hiding (UDH). We demonstrate the capabilities and limitations of SUDS by answering five research questions, including baseline comparisons and an ablation study. Additionally, we apply SUDS to a real-world scenario, where it is able to increase the resistance of a poisoned classifier against attacks by 1375%.
- Open Access
SUDS: Sanitizing Universal and Dependent Steganography
Steganography, or hiding messages in plain sight, is a form of information hiding that is most commonly used for covert communication. As modern steganographic mediums include images, text, audio, and video, this communication method is being increasingly used by bad actors to propagate malware, exfiltrate data, and discreetly communicate. Current protection mechanisms rely upon steganalysis, or the detection of steganography, but these approaches are dependent upon prior knowledge, such as steganographic signatures from publicly available tools and statistical knowledge about known hiding methods. These dependencies render steganalysis useless against new or unique hiding methods, which are becoming increasingly common with the application of deep learning models. To mitigate the shortcomings of steganalysis, this work focuses on a deep learning sanitization technique called SUDS that is not reliant upon knowledge of steganographic hiding techniques and is able to sanitize universal and dependent steganography. SUDS is tested using least significant bit method (LSB), dependent deep hiding (DDH), and universal deep hiding (UDH). We demonstrate the capabilities and limitations of SUDS by answering five research questions, including baseline comparisons and an ablation study. Additionally, we apply SUDS to a real-world scenario, where it is able to increase the resistance of a poisoned classifier against attacks by 1375%.
Open AccessSUDS: Sanitizing Universal and Dependent Steganography
Steganography, or hiding messages in plain sight, is a form of information hiding that is most commonly used for covert communication. As modern steganographic mediums include images, text, audio, and video, this communication method is being increasingly used by bad actors to propagate malware, exfiltrate data, and discreetly communicate. Current protection mechanisms rely upon steganalysis, or the detection of steganography, but these approaches are dependent upon prior knowledge, such as steganographic signatures from publicly available tools and statistical knowledge about known hiding methods. These dependencies render steganalysis useless against new or unique hiding methods, which are becoming increasingly common with the application of deep learning models. To mitigate the shortcomings of steganalysis, this work focuses on a deep learning sanitization technique called SUDS that is not reliant upon knowledge of steganographic hiding techniques and is able to sanitize universal and dependent steganography. SUDS is tested using least significant bit method (LSB), dependent deep hiding (DDH), and universal deep hiding (UDH). We demonstrate the capabilities and limitations of SUDS by answering five research questions, including baseline comparisons and an ablation study. Additionally, we apply SUDS to a real-world scenario, where it is able to increase the resistance of a poisoned classifier against attacks by 1375%.