Search for: All records

As the semiconductor industry has shifted to a fabless paradigm, the risk of hardware Trojans being inserted at various stages of production has also increased. Recently, there has been a growing trend toward the use of machine learning solutions to effectively detect hardware Trojans with a focus on the accuracy of the model as an evaluation metric. However, in a high-risk and sensitive domain, we cannot accept even a small misclassification. Additionally, it is unrealistic to expect an ideal model, especially when Trojans evolve over time. In this paper, we design an uncertainty-aware machine learning solution which also handles evolving hardware Trojans using our proposed novel conformalized generative adversarial network. We further extend the proposed method for multimodal deep learning along with uncertainty quantification that also addresses the problem of missing modalities. The proposed solutions have been validated on both synthetic and real chip-level benchmarks and proven to pave the way for researchers looking to find informed machine learning solutions to hardware security problems. 

Evolving Hardware Trojans pose a serious threat to modern digital systems by evading traditional detection through stealthy, adaptive behavior. Even recent methods that leverage advances in machine learning can only detect them after activation, leaving a critical window for potential security breaches. To address this gap, we propose a novel approach for hardware Trojan detection and prediction using Neural Controlled Differential Equations (NCDEs) and analysis of power traces. Our method leverages an NCDE model trained exclusively on Trojan-free data to learn nominal power behavior, combined with a Linear Discriminant Analysis (LDA) classifier calibrated on labeled data, to distinguish between three scenarios: no Trojan, dormant Trojan, and active Trojan. Our method uses a sliding window to process side-channel measurements, enabling detection of subtle power consumption deviations that indicate Trojan presence, even when dormant. Experimental results demonstrate that the proposed NCDE-based method achieves superior accuracy compared to traditional machine learning approaches, with the additional advantage of handling dormant Trojans above a sensitivity threshold. We validate our approach on standard hardware Trojan benchmarks, showing robust detection and prediction performance. 

Detecting Common Weakness Enumerations (CWEs) in computational systems remains a challenge for hardware and software developers. In this paper, we scrutinize the efficacy of machine learning algorithms in addressing the above issue, employing both real and synthetic data generated via data augmentation techniques, generative adversarial networks, and rule-based synthesis. Furthermore, we propose fine-tuning Large Language Models (LLMs) to generate two high-quality CWE datasets of 50,000 entries each. We then deploy traditional machine learning algorithms such as support vector classifier, random forest, and naive Bayes, as well as advanced methods such as convolutional neural networks, graph neural networks, and transformer-based architectures, on the curated dataset to perform the task of CWE detection. Results show that finetuned LLMs and transformer architectures outperform others, demonstrating their effectiveness in identifying vulnerabilities across hardware-software boundaries. 

The risk of hardware Trojans being inserted at various stages of chip production has increased in a zero-trust fabless era. To counter this, various machine learning solutions have been developed for the detection of hardware Trojans. While most of the focus has been on either a statistical or deep learning approach, the limited number of Trojan-infected benchmarks affects the detection accuracy and restricts the possibility of detecting zero-day Trojans. To close the gap, we first employ generative adversarial networks to amplify our data in two alternative representation modalities: a graph and a tabular, which ensure a representative distribution of the dataset. Further, we propose a multimodal deep learning approach to detect hardware Trojans and evaluate the results from both early fusion and late fusion strategies. We also estimate the uncertainty quantification metrics of each prediction for risk-aware decision-making. The results not only validate the effectiveness of our suggested hardware Trojan detection technique but also pave the way for future studies utilizing multimodality and uncertainty quantification to tackle other hardware security problems. 

As the semiconductor industry has shifted to a fabless paradigm, the risk of hardware Trojans being inserted at various stages of production has also increased. Recently, there has been a growing trend toward the use of machine learning solutions to detect hardware Trojans more effectively, with a focus on the accuracy of the model as an evaluation metric. However, in a high-risk and sensitive domain, we cannot accept even a small misclassification. Additionally, it is unrealistic to expect an ideal model, especially when Trojans evolve over time. Therefore, we need metrics to assess the trustworthiness of detected Trojans and a mechanism to simulate unseen ones. In this paper, we generate evolving hardware Trojans using our proposed novel conformalized generative adversarial networks and offer an efficient approach to detecting them based on a non-invasive algorithm-agnostic statistical inference framework that leverages the Mondrian conformal predictor. The method acts like a wrapper over any of the machine learning models and produces set predictions along with uncertainty quantification for each new detected Trojan for more robust decision-making. In the case of a NULL set, a novel method to reject the decision by providing a calibrated explainability is discussed. The proposed approach has been validated on both synthetic and real chip-level benchmarks and proven to pave the way for researchers looking to find informed machine learning solutions to hardware security problems. 

Abstract Chaos is a deterministic phenomenon that occurs in a non-linear dynamic system under specific condition when the trajectories of the state vector become periodic and extremely sensitive to the initial conditions. While traditional resistor-based chaotic communications are primarily concerned with the safe transfer of information across networks, the transceivers themselves can be compromised due to outsource manufacturing. With the growth of wireless sensors in resource-constrained implantable and wearable devices, chaotic communication may be a good fit if the information transmitted is reliable and the transmitter devices are secure. We believe that memristor, as the fourth fundamental two-terminal circuit element, can close the gap between reliable communication and secure manufacturing since its resistance can be programmed and saved by the designer and not the foundry. Thus, in this paper, we propose a memristor-based Chua’s chaotic transceiver that is both reliable in the presence of eavesdroppers and secure against untrusted foundries. Specifically, we consider the pair of transmitter and receiver under the same memristor value to show the possibility of uninterrupted communication as well as cases where different values of memristors are used to find out the possible range in which the message can still be meaningfully decoded. Experimental results confirm that both reliable communication and secure design can be achieved via our proposed memristor-based chaos transceivers. 

The Global Wearable market is anticipated to rise at a considerable rate in the next coming years and communication is a fundamental block in any wearable device. In communication, encryption methods are being used with the aid of microcontrollers or software implementations, which are power-consuming and incorporate complex hardware implementation. Internet of Things (IoT) devices are considered as resource-constrained devices that are expected to operate with low computational power and resource utilization criteria. At the same time, recent research has shown that IoT devices are highly vulnerable to emerging security threats, which elevates the need for low-power and small-size hardware-based security countermeasures. Chaotic encryption is a method of data encryption that utilizes chaotic systems and non-linear dynamics to generate secure encryption keys. It aims to provide high-level security by creating encryption keys that are sensitive to initial conditions and difficult to predict, making it challenging for unauthorized parties to intercept and decode encrypted data. Since the discovery of chaotic equations, there have been various encryption applications associated with them. In this paper, we comprehensively analyze the physical and encryption attacks on continuous chaotic systems in resource-constrained devices and their potential remedies. To this aim, we introduce different categories of attacks of chaotic encryption. Our experiments focus on chaotic equations implemented using Chua’s equation and leverages circuit architectures and provide simulations proof of remedies for different attacks. These remedies are provided to block the attackers from stealing users’ information (e.g., a pulse message) with negligible cost to the power and area of the design.