Amir Sadovnik
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Amir Sadovnik has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Arka Daw
Oak Ridge National Laboratory
1 shared publication - David S. Bolme
Oak Ridge National Laboratory
1 shared publication - Edmon Begoli
Oak Ridge National Laboratory
1 shared publication - Fabian Fallas-Moya
Universidad de Costa Rica
1 shared publication - Hairong Qi
Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN 37996, USA
1 shared publication - Joel Brogan
Oak Ridge National Laboratory
1 shared publication
Latest Publications
- 26 July 2025
- Published by Springer Nature
- p. 289-302
Bridging the Gap from Research to Reality: Methods for Fortifying Mitigation Measures Against Adversarial AI
- 26 July 2025
- Published by Springer Nature
- p. 289-302
Bridging the Gap from Research to Reality: Methods for Fortifying Mitigation Measures Against Adversarial AI
- Open Access
- 8 April 2025
- Published by Instituto Tecnologico de Costa Rica in Revista Tecnología en Marcha
- p. ág. 100-111
Adding a teaching “assistant”: improving the quality of pseudo-labels for semi-supervised object detection
This paper focuses on semi-supervised object detection (SS-OD) for its tolerance to small amounts of training samples, which is common in real-world applications. Pseudo-label-based approaches have been the mainstream for SS-OD. In this paper, we first show the impact of accurate pseudo-labeling and the challenge of producing such labels. In contrast to prior research that predominantly focused on refining the main model to enhance localization, this paper introduces a novel strategy, where a standalone “Teaching Assistant” or simply “Assistant” is involved in the popular Teacher/Student paradigm to improve the quality of pseudo-labels. This “Assistant” can be plugged into any existing Teacher/Student-based framework without having to fine-tune the original Teacher/Student model. We exploit two “Assistant” models, both of which center around the non-maximum suppression (NMS) method -- a popular technique used to select only the promising bounding boxes. The first “Assistant” model is referred to as the “pre-NMS” assistant that refines the candidate bounding box scores for a better set of inputs to the NMS process. The second “Assistant” model is referred to as the “post-NMS” assistant which takes advantage of SOTA segmentation models to improve the output from the NMS process. We thoroughly evaluate the performance of pre-NMS vs. post-NMS and the impact of improved pseudo-labels on the OD performance. Experimental results on the COCO dataset demonstrate that post-NMS is better than SOTA methods.
- 8 April 2025
- Published by Instituto Tecnologico de Costa Rica in Revista Tecnología en Marcha
- p. ág. 100-111
Open AccessAdding a teaching “assistant”: improving the quality of pseudo-labels for semi-supervised object detection
This paper focuses on semi-supervised object detection (SS-OD) for its tolerance to small amounts of training samples, which is common in real-world applications. Pseudo-label-based approaches have been the mainstream for SS-OD. In this paper, we first show the impact of accurate pseudo-labeling and the challenge of producing such labels. In contrast to prior research that predominantly focused on refining the main model to enhance localization, this paper introduces a novel strategy, where a standalone “Teaching Assistant” or simply “Assistant” is involved in the popular Teacher/Student paradigm to improve the quality of pseudo-labels. This “Assistant” can be plugged into any existing Teacher/Student-based framework without having to fine-tune the original Teacher/Student model. We exploit two “Assistant” models, both of which center around the non-maximum suppression (NMS) method -- a popular technique used to select only the promising bounding boxes. The first “Assistant” model is referred to as the “pre-NMS” assistant that refines the candidate bounding box scores for a better set of inputs to the NMS process. The second “Assistant” model is referred to as the “post-NMS” assistant which takes advantage of SOTA segmentation models to improve the output from the NMS process. We thoroughly evaluate the performance of pre-NMS vs. post-NMS and the impact of improved pseudo-labels on the OD performance. Experimental results on the COCO dataset demonstrate that post-NMS is better than SOTA methods.
- Open Access
Advancing NLP Security by Leveraging LLMs as Adversarial Engines
This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse adversarial attacks. Building upon recent work demonstrating LLMs' effectiveness in creating word-level adversarial examples, we argue for expanding this concept to encompass a broader range of attack types, including adversarial patches, universal perturbations, and targeted attacks. We posit that LLMs' sophisticated language understanding and generation capabilities can produce more effective, semantically coherent, and human-like adversarial examples across various domains and classifier architectures. This paradigm shift in adversarial NLP has far-reaching implications, potentially enhancing model robustness, uncovering new vulnerabilities, and driving innovation in defense mechanisms. By exploring this new frontier, we aim to contribute to the development of more secure, reliable, and trustworthy NLP systems for critical applications.
Open AccessAdvancing NLP Security by Leveraging LLMs as Adversarial Engines
This position paper proposes a novel approach to advancing NLP security by leveraging Large Language Models (LLMs) as engines for generating diverse adversarial attacks. Building upon recent work demonstrating LLMs' effectiveness in creating word-level adversarial examples, we argue for expanding this concept to encompass a broader range of attack types, including adversarial patches, universal perturbations, and targeted attacks. We posit that LLMs' sophisticated language understanding and generation capabilities can produce more effective, semantically coherent, and human-like adversarial examples across various domains and classifier architectures. This paradigm shift in adversarial NLP has far-reaching implications, potentially enhancing model robustness, uncovering new vulnerabilities, and driving innovation in defense mechanisms. By exploring this new frontier, we aim to contribute to the development of more secure, reliable, and trustworthy NLP systems for critical applications.