Related papers: Attacking AI Accelerators by Leveraging Arithmetic…

Backdoors pose a serious threat to machine learning, as they can compromise the integrity of security-critical systems, such as self-driving cars. While different defenses have been proposed to address this threat, they all rely on the…

Adversarial training (AT) with projected gradient descent is the most popular method to improve model robustness under adversarial attacks. However, computational overheads become prohibitively large when AT is applied to large backbone…

The transition to smart grids has increased the vulnerability of electrical power systems to advanced cyber threats. To safeguard these systems, comprehensive security measures-including preventive, detective, and reactive strategies-are…

Memristors have recently received significant attention as ubiquitous device-level components for building a novel generation of computing systems. These devices have many promising features, such as non-volatility, low power consumption,…

We present a time complexity analysis of the Opt-IA artificial immune system (AIS). We first highlight the power and limitations of its distinguishing operators (i.e., hypermutations with mutation potential and ageing) by analysing them in…

Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the…

The alternating direction method of multipliers (ADMM) is a powerful operator splitting technique for solving structured convex optimization problems. Due to its relatively low per-iteration computational cost and ability to exploit…

The widespread use of generative AI has shown remarkable success in producing highly realistic deepfakes, posing a serious threat to various voice biometric applications, including speaker verification, voice biometrics, audio conferencing,…

The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs. While this enabled us to train large-scale neural networks in datacenters and deploy them on edge devices, the…

This research introduces an FPGA-based hardware accelerator to optimize the Singular Value Decomposition (SVD) and Fast Fourier transform (FFT) operations in AI models. The proposed design aims to improve processing speed and reduce…

Adversarial attacks are a potential threat to machine learning models by causing incorrect predictions through imperceptible perturbations to the input data. While these attacks have been extensively studied in unstructured data like…

Experimental evidence confirms that AI tools raise worker productivity, but also that sustained use can erode the expertise on which those gains depend. We develop a dynamic model in which a decision-maker chooses AI usage intensity for a…

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…

Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…

Recent hardware acceleration advances have enabled powerful specialized accelerators for finite element computations, spiking neural network inference, and sparse tensor operations. However, existing approaches face fundamental limitations:…

Brain-inspired computing aims to mimic cognitive functions like associative memory, the ability to recall complete patterns from partial cues. Memristor technology offers promising hardware for such neuromorphic systems due to its potential…

In the seller-buyer setting on machine learning models, the seller generates different copies based on the original model and distributes them to different buyers, such that adversarial samples generated on one buyer's copy would likely not…

Inference efficiency is the predominant consideration in designing deep learning accelerators. Previous work mainly focuses on skipping zero values to deal with remarkable ineffectual computation, while zero bits in non-zero values, as…

In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are…

Transformer-based pre-trained models of code (PTMC) have been widely utilized and have achieved state-of-the-art performance in many mission-critical applications. However, they can be vulnerable to adversarial attacks through identifier…