Damon L. Woodard

David Selasi Koblah, Rabin Yu Acharya, Daniel Capecci et al.

Artificial intelligence (AI) and machine learning (ML) techniques have been increasingly used in several fields to improve performance and the level of automation. In recent years, this use has exponentially increased due to the advancement of high-performance computing and the ever increasing size of data. One of such fields is that of hardware design; specifically the design of digital and analog integrated circuits~(ICs), where AI/ ML techniques have been extensively used to address ever-increasing design complexity, aggressive time-to-market, and the growing number of ubiquitous interconnected devices (IoT). However, the security concerns and issues related to IC design have been highly overlooked. In this paper, we summarize the state-of-the-art in AL/ML for circuit design/optimization, security and engineering challenges, research in security-aware CAD/EDA, and future research directions and needs for using AI/ML for security-aware circuit design.

Ronald Wilson, Avanti Bhandarkar, Damon Woodard

Stylistic analysis of text is a key task in research areas ranging from authorship attribution to forensic analysis and personality profiling. The existing approaches for stylistic analysis are plagued by issues like topic influence, lack of discriminability for large number of authors and the requirement for large amounts of diverse data. In this paper, the source of these issues are identified along with the necessity for a cognitive perspective on authorial style in addressing them. A novel feature representation, called Trajectory-based Style Estimation (TraSE), is introduced to support this purpose. Authorship attribution experiments with over 27,000 authors and 1.4 million samples in a cross-domain scenario resulted in 90% attribution accuracy suggesting that the feature representation is immune to such negative influences and an excellent candidate for stylistic analysis. Finally, a qualitative analysis is performed on TraSE using physical human characteristics, like age, to validate its claim on capturing cognitive traits.

Avanti Bhandarkar, Ronald Wilson, Anushka Swarup et al.

In the era of generative AI, the widespread adoption of Neural Text Generators (NTGs) presents new cybersecurity challenges, particularly within the realms of Digital Forensics and Incident Response (DFIR). These challenges primarily involve the detection and attribution of sources behind advanced attacks like spearphishing and disinformation campaigns. As NTGs evolve, the task of distinguishing between human and NTG-authored texts becomes critically complex. This paper rigorously evaluates the DFIR pipeline tailored for text-based security systems, specifically focusing on the challenges of detecting and attributing authorship of NTG-authored texts. By introducing a novel human-NTG co-authorship text attack, termed CS-ACT, our study uncovers significant vulnerabilities in traditional DFIR methodologies, highlighting discrepancies between ideal scenarios and real-world conditions. Utilizing 14 diverse datasets and 43 unique NTGs, up to the latest GPT-4, our research identifies substantial vulnerabilities in the forensic profiling phase, particularly in attributing authorship to NTGs. Our comprehensive evaluation points to factors such as model sophistication and the lack of distinctive style within NTGs as significant contributors for these vulnerabilities. Our findings underscore the necessity for more sophisticated and adaptable strategies, such as incorporating adversarial learning, stylizing NTGs, and implementing hierarchical attribution through the mapping of NTG lineages to enhance source attribution. This sets the stage for future research and the development of more resilient text-based security systems.

Anushka Swarup, Avanti Bhandarkar, Olivia P. Dizon-Paradis et al.

Relation extraction is a Natural Language Processing task that aims to extract relationships from textual data. It is a critical step for information extraction. Due to its wide-scale applicability, research in relation extraction has rapidly scaled to using highly advanced neural networks. Despite their computational superiority, modern relation extractors fail to handle complicated extraction scenarios. However, a comprehensive performance analysis of the state-of-the-art extractors that compile these challenges has been missing from the literature, and this paper aims to bridge this gap. The goal has been to investigate the possible data-centric characteristics that impede neural relation extraction. Based on extensive experiments conducted using 15 state-of-the-art relation extraction algorithms ranging from recurrent architectures to large language models and seven large-scale datasets, this research suggests that modern relation extractors are not robust to complex data and relation characteristics. It emphasizes pivotal issues, such as contextual ambiguity, correlating relations, long-tail data, and fine-grained relation distributions. In addition, it sets a marker for future directions to alleviate these issues, thereby proving to be a critical resource for novice and advanced researchers. Efficient handling of the challenges described can have significant implications for the field of information extraction, which is a critical part of popular systems such as search engines and chatbots. Data and relevant code can be found at \url{https://aaig.ece.ufl.edu/projects/relation-extraction}.

Stephen Wormald, David Koblah, Matheus Kunzler Maldaner et al.

Constraining deep neural networks (DNNs) to learn individual logic types per node, as performed using the DiffLogic network architecture, opens the door to model-specific explanation techniques that quell the complexity inherent to DNNs. Inspired by principles of circuit analysis from computer engineering, this work presents an algorithm (eXpLogic) for producing saliency maps which explain input patterns that activate certain functions. The eXpLogic explanations: (1) show the exact set of inputs responsible for a decision, which helps interpret false negative and false positive predictions, (2) highlight common input patterns that activate certain outputs, and (3) help reduce the network size to improve class-specific inference. To evaluate the eXpLogic saliency map, we introduce a metric that quantifies how much an input changes before switching a model's class prediction (the SwitchDist) and use this metric to compare eXpLogic against the Vanilla Gradients (VG) and Integrated Gradient (IG) methods. Generally, we show that eXpLogic saliency maps are better at predicting which inputs will change the class score. These maps help reduce the network size and inference times by 87\% and 8\%, respectively, while having a limited impact (-3.8\%) on class-specific predictions. The broader value of this work to machine learning is in demonstrating how certain DNN architectures promote explainability, which is relevant to healthcare, defense, and law.

Tianyu Bell Pan, Mengdi Zhu, Alexa Jordyn Cole et al.

Multimodal learning systems often struggle in non-stationary environments due to concept drift, where changing data distributions can degrade performance. Modality-specific drifts and the lack of mechanisms for continuous, stable adaptation compound this challenge. This paper introduces LS-OGD, a novel adaptive control framework for robust multimodal learning in the presence of concept drift. LS-OGD uses an online controller that dynamically adjusts the model's learning rate and the fusion weights between different data modalities in response to detected drift and evolving prediction errors. We prove that under bounded drift conditions, the LS-OGD system's prediction error is uniformly ultimately bounded and converges to zero if the drift ceases. Additionally, we demonstrate that the adaptive fusion strategy effectively isolates and mitigates the impact of severe modality-specific drift, thereby ensuring system resilience and fault tolerance. These theoretical guarantees establish a principled foundation for developing reliable and continuously adapting multimodal learning systems.

Tianyu Bell Pan, Damon L. Woodard

This paper explores a multimodal co-training framework designed to enhance model generalization in situations where labeled data is limited and distribution shifts occur. We thoroughly examine the theoretical foundations of this framework, deriving conditions under which the use of unlabeled data and the promotion of agreement between classifiers for different modalities lead to significant improvements in generalization. We also present a convergence analysis that confirms the effectiveness of iterative co-training in reducing classification errors. In addition, we establish a novel generalization bound that, for the first time in a multimodal co-training context, decomposes and quantifies the distinct advantages gained from leveraging unlabeled multimodal data, promoting inter-view agreement, and maintaining conditional view independence. Our findings highlight the practical benefits of multimodal co-training as a structured approach to developing data-efficient and robust AI systems that can effectively generalize in dynamic, real-world environments. The theoretical foundations are examined in dialogue with, and in advance of, established co-training principles.

Nathan Jessurun, Olivia P. Dizon-Paradis, Jacob Harrison et al.

Outsourced printed circuit board (PCB) fabrication necessitates increased hardware assurance capabilities. Several assurance techniques based on automated optical inspection (AOI) have been proposed that leverage PCB images acquired using digital cameras. We review state-of-the-art AOI techniques and observe a strong, rapid trend toward machine learning (ML) solutions. These require significant amounts of labeled ground truth data, which is lacking in the publicly available PCB data space. We contribute the FICS PCB Image Collection (FPIC) dataset to address this need. Additionally, we outline new hardware security methodologies enabled by our data set.

Ronald Wilson, Navid Asadizanjani, Domenic Forte et al.

In the Reverse Engineering and Hardware Assurance domain, a majority of the data acquisition is done through electron microscopy techniques such as Scanning Electron Microscopy (SEM). However, unlike its counterparts in optical imaging, only a limited number of techniques are available to enhance and extract information from the raw SEM images. In this paper, we introduce an algorithm to segment out Integrated Circuit (IC) structures from the SEM image. Unlike existing algorithms discussed in this paper, this algorithm is unsupervised, parameter-free and does not require prior information on the noise model or features in the target image making it effective in low quality image acquisition scenarios as well. Furthermore, the results from the application of the algorithm on various structures and layers in the IC are reported and discussed.

Ulbert J. Botero, Ronald Wilson, Hangwei Lu et al.

In the context of hardware trust and assurance, reverse engineering has been often considered as an illegal action. Generally speaking, reverse engineering aims to retrieve information from a product, i.e., integrated circuits (ICs) and printed circuit boards (PCBs) in hardware security-related scenarios, in the hope of understanding the functionality of the device and determining its constituent components. Hence, it can raise serious issues concerning Intellectual Property (IP) infringement, the (in)effectiveness of security-related measures, and even new opportunities for injecting hardware Trojans. Ironically, reverse engineering can enable IP owners to verify and validate the design. Nevertheless, this cannot be achieved without overcoming numerous obstacles that limit successful outcomes of the reverse engineering process. This paper surveys these challenges from two complementary perspectives: image processing and machine learning. These two fields of study form a firm basis for the enhancement of efficiency and accuracy of reverse engineering processes for both PCBs and ICs. In summary, therefore, this paper presents a roadmap indicating clearly the actions to be taken to fulfill hardware trust and assurance objectives.

Nima Karimian, Zimu Guo, Fatemeh Tehranipoor et al.

With the emergence of the Internet-of-Things (IoT), there is a growing need for access control and data protection on low-power, pervasive devices. Biometric-based authentication is promising for IoT due to its convenient nature and lower susceptibility to attacks. However, the costs associated with biometric processing and template protection are nontrivial for smart cards, key fobs, and so forth. In this paper, we discuss the security, cost, and utility of biometric systems and develop two major frameworks for improving them. First, we introduce a new framework for implementing biometric systems based on physical unclonable functions (PUFs) and hardware obfuscation that, unlike traditional software approaches, does not require nonvolatile storage of a biometric template/key. Aside from reducing the risk of compromising the biometric, the nature of obfuscation also provides protection against access control circumvention via malware and fault injection. The PUF provides non-invertibility and non-linkability. Second, a major requirement of the proposed PUF/obfuscation approach is that a reliable (robust) key be generated from the users input biometric. We propose a noiseaware biometric quantization framework capable of generating unique, reliable keys with reduced enrollment time and denoising costs. Finally, we conduct several case studies. In the first, the proposed noise-aware approach is compared to our previous approach for multiple biometric modalities, including popular ones (fingerprint and iris) and emerging cardiovascular ones (ECG and PPG). The results show that ECG provides the best tradeoff between reliability, key length, entropy, and cost. In the second and third case studies, we demonstrate how reliability, denoising costs, and enrollment times can be simultaneously improved by modeling subject intra-variations for ECG.