As AI workloads drive increases in datacenter power consumption, accurate GPU power estimation is critical for proactive power management. However, existing power models face a scalability bottleneck not in the modeling techniques themselves, but in obtaining the hardware utilization inputs they require. Conventional approaches rely on either costly simulation or hardware profiling, which makes them impractical when rapid predictions are required. This work presents EnergAIzer, which addresses this scalability bottleneck by developing a lightweight solution to predict utilization inputs, reducing the estimation walltime from hours to seconds. Our key insight is that kernels in AI workloads commonly employ optimizations that create structured patterns, which analytically determine memory traffic and execution timeline. We construct a performance model using these patterns as an analytical scaffold for empirical data fitting, which also naturally exposes module-level utilization. This predicted utilization is then fed into our power model to estimate dynamic power consumption. EnergAIzer achieves $8 \%$ power errors on NVIDIA Ampere GPUs, competitive with traditional power models with elaborate cycle-level simulation or hardware profiling. We demonstrate EnergAIzer’s exploration capabilities for frequency scaling and architectural configurations, including forecasting the power of NVIDIA H100 with just $7 \%$ error. In summary, EnergAIzer provides fast and accurate power prediction for AI workloads, paving the way for power-aware design explorations.

Research in behavioral biometrics, especially keystroke and mouse behavioral biometrics, has increased in recent years, gaining traction in industry and academia across various fields, including the detection of emotion, age, gender, fatigue, identity theft, and online assessment fraud. These methods are popular because they collect data non-invasively and continuously authenticate users by analyzing unique keystroke or mouse behavior. However, user behavior evolves over time due to several underlying factors. This can affect the performance of current keystroke and mouse behavioral biometric-based user authentication systems. We comprehensively survey current keystroke and mouse behavioral biometric approaches, exploring their use in user authentication and other real-world applications while outlining trends and research gaps. In particular, we investigate whether current approaches compensate for user behavior evolution. We find that current keystroke and mouse behavioral biometrics approaches cannot adapt to user behavior evolution and suffer from limited efficacy. Our survey highlights the need for new and improved keystroke and mouse behavioral biometrics approaches that can adapt to user behavior evolution. This study will assist researchers in improving current research efforts toward developing more secure, effective, sustainable, robust, adaptable, and privacy-preserving keystroke and mouse-behavioral biometric-based authentication systems.

Security vulnerabilities in deep neural network (DNN) accelerators pose risks for high-stakes applications, with off-chip memory attacks representing a critical threat to both data confidentiality and integrity. While general-purpose processors employ comprehensive cryptographic authenticated encryption for memory security, domain-specific DNN accelerators lack adequate protection, particularly against integrity violations. To address this research gap, we present Sorbet, a DNN accelerator equipped with authenticated encryption to defend against both confidentiality and integrity attacks on off-chip memory. Integrity verification introduces complex memory access patterns in DNN accelerators, as the granularity of authentication operations often clashes with the tiling strategies used for efficient off-chip memory access. Our approach tackles this challenge with a secure memory interface (SMI) module that efficiently: 1) translates the accelerator’s tile request to the required data for cryptographic authentication and 2) aligns fetched data with the memory map of the accelerator’s on-chip buffers. Moreover, our design mitigates the area and performance overhead of cryptographic operations by adopting a lightweight cipher while maintaining security requirements against splicing and replay attacks. Our fabricated chip achieves 22% latency overhead across diverse workloads, including convolutions and multihead attentions (MHAs), which can be further reduced with larger on-chip buffer size and double-buffering. It incurs only 7.9% area and 18.3% energy overhead, which is competitive with recent DNN accelerator defenses with weaker off-chip memory protection.

Mouse behavioral biometric-based authentication systems have attracted significant attention as they are considered a more secure alternative to conventional online assessment fraud detection systems. This is attributed to their ability to continuously authenticate users non-intrusively by analyzing their distinctive mouse operating behavior. Most behavioral biometric-based research studies focus on predicting user identity as the primary objective for online assessment fraud detection. However, they do not consider predicting other user-centric parameters like age and gender. Furthermore, there is a need to identify the best segmentation approach and mouse behavior feature set for age and gender classification. We propose the AgeGen Bio track system, a continuous mouse behavioral biometric-based age and gender tracking system for online education platforms. To accomplish this, we first collect novel mouse behavior data with user demographic information. We then evaluate the efficacy of different segmentation approaches, feature sets, and machine learning models for age and gender classification. Experimental results show that the random forest algorithm paired with the three mouse-movement segmentation approach and user characteristic feature set are the best approaches that need to be incorporated into the system, as they achieved promising results.

Devices on the Internet of Things (IoT) often have constrained resources and operate in diverse environments, making them vulnerable to unauthorized access and cyber threats. Electrocardiogram (ECG) signals have emerged as a promising biometric for authenticating users in such settings. However, current ECG-based authentication studies lack a standardized evaluation framework tailored to resource-limited IoT contexts and long-term usage, making it difficult to assess their practical reliability. In this paper, we introduce a new evaluation framework for ECG-based authentication on IoT devices and construct a standardized dataset to facilitate rigorous testing. We categorize performance metrics into four key dimensions: scalability, adaptability, efficiency, and cancelability. Using this framework, we evaluate four representative ECG authentication algorithms for IoT devices. The results show that these algorithms struggle to maintain consistent performance under cross-session authentication scenarios. These findings highlight the critical importance of addressing the temporal variability of ECG signals and the current gap in robust ECG-based authentication for IoT devices. We believe the proposed framework will guide future research toward more resilient and secure ECG authentication systems for the IoT.

Recent developments in mobile computing power and wireless communication speeds have significantly improved the efficiency of medical systems. This paper focuses on passive wearable sensor devices, which are integral to noninvasive monitoring of physiological data in healthcare observation. Beyond data collection, some wearables play an active role in patient treatment, underscoring the critical importance of protecting their security and privacy. Breach in these areas can severely affect patient health. However, the distinctive characteristics of wearable technologies introduce unique security and privacy challenges, including the potential for unauthorized access to sensitive location, medical, and physiological data. This review delves into the security and privacy concerns associated with wearable devices and proposes potential remedies. Its value lies in providing insights for researchers and manufacturers, aiming to advance the development of safer and more effective wearable medical technologies.

Online education systems have gained immense popularity due to their ubiquity, flexibility, openness, and accessibility. This has led many higher education institutions to incorporate online courses as part of blended or fully online learning. However, online assessment fraud remains a critical challenge. Conventional assessment fraud detection methods are often one-time, non-repudiable, invasive, expensive, and susceptible to spoofing. Even some advanced systems based on behavioral biometrics report comparatively lower accuracy, underscoring the ongoing challenge of achieving reliable user authentication. Furthermore, few research studies focus on behavioral biometric-based assessment fraud detection in online education platforms. To address these gaps, we introduce the UserID.AGE.GEN framework, which implements a cross-referencing fusion algorithm that integrates user demographic parameters, including age and gender, with mouse behavioral biometrics for user identity verification for online assessment fraud. Additionally, we collect novel task-specific data for our evaluation. Experimental results demonstrate that our method achieves promising results compared to some existing models, highlighting its strong performance and promising potential for broader application and future enhancement. A notable limitation of the proposed model is that it has not yet been evaluated using significantly larger external datasets, which may affect the generalizability of the results. Our evaluation was conducted using internally collected datasets. Additionally, the model has not been tested in real-world settings such as online education platforms, which may limit insights into its practical deployment.

Electrocardiogram(ECG)-based biometric authentication has become a promising method to improve security in wearable devices due to its inherent uniqueness and difficulty to replicate. However, no studies currently demonstrate that ECG authentication can resist modern attack techniques employed against biometric authentication. In this paper, we present a novel dictionary attack against ECG authentication systems, which poses a significant threat. In contrast to conventional targeted attacks, this approach utilizes random pairing to breach a vast number of users, without requiring specific information about their biometric data. Our approach leverages adversarial optimization and clustering to generate synthetic ECG waveforms capable of bypassing authentication mechanisms of various systems, revealing critical vulnerabilities in the current implementation of ECG-based biometrics. We comprehensively evaluate the effectiveness of this attack across different ECG authentication models, demonstrating that despite the intrinsic uniqueness of ECG signals, a substantial number of users are vulnerable. Our attack method can bypass the authentication system of an average of 20% of users even at the most stringent false acceptance rate of 1%. With up to five attack attempts allowed, our method can bypass up to 62% of users’ ECG authentication models.

In recent times, electrocardiogram signals have been leveraged for biometric verification. The efficacy of such authentication is reliant on the feature extraction from the electrocardiogram signals. A number of electrocardiogram feature extraction methods are currently available, but these methods may not be universally applicable in different dataset collection scenarios. To tackle this issue, this paper introduces a clustering-based framework to assess the feature extraction techniques for electrocardiogram biometrics. In this paper, the effectiveness of the framework is validated by using different electrocardiogram feature extraction techniques and different electrocardiogram databases. The framework provides important insights into electrocardiogram signal.

Deep neural networks (DNNs) are gaining popularity in a wide range of domains, ranging from speech and video recognition to healthcare. With this increased adoption comes the pressing need for securing DNN execution environments on CPUs, GPUs, and ASICs. While there are active research efforts in supporting a trusted execution environment (TEE) on CPUs, the exploration in supporting TEEs on accelerators is limited, with only a few solutions available [18, 19, 27]. A key limitation along this line of work is that these secure DNN accelerators narrowly consider a few specific architectures. The design choices and the associated cost for securing these architectures do not transfer to other diverse architectures.

Deep neural networks (DNNs) are shown to be vulnerable to a few carefully chosen bit flips in their parameters, and bit flip attacks (BFAs) exploit such vulnerability to degrade the performance of DNNs. In this work, we show that DNNs with high sparsity that typically result from weight pruning have a unique source of vulnerability to bit flips when their coordinates of nonzero weights are attacked. We propose SparseBFA, an algorithm that searches for a small number of bits among the coordinates of nonzero weights when the parameters of DNNs are stored using sparse matrix formats. Using SparseBFA, we find that the performance of DNNs drops to the random-guess level by flipping less than 0.00005% (1 in 2 million) of the total bits.

Increasing geotagged social media data has become a potential repository used to find common trajectory patterns. Various spatial trajectory behaviors have been studied in previous work. In this paper, we extract common trajectory patterns on semantic level. We enrich trajectories with additional contextual semantic annotations and propose a density-based method to find semantic common trajectory patterns with a novel similarity measure method. Real geotagged photo data are used in our experiments. Experimental results demonstrate that our methods are able to generate semantic common trajectory patterns.

A-scans from ultrasonic testing of long shafts are complex signals. The discrimination of different types of echoes is of importance for nondestructive testing and equipment maintenance. Research has focused on selecting features of physical significance or exploring classifier like artificial neural networks and support vector machines. This paper confirms the observation that there seems to be uncorrelated errors among the variants explored in the past, and therefore an ensemble of classifiers is to achieve better discrimination accuracy. We explore the diverse possibilities of heterogeneous and homogeneous ensembles, combination techniques, feature extraction methods and classifiers types and determine guidelines for heterogeneous combinations that result in superior performance.