Related papers: Attacking AI Accelerators by Leveraging Arithmetic…

We study how artificial intelligence (AI) affects firms' incentives to pursue incremental versus radical knowledge recombinations. We develop a model of recombinant innovation embedded in a Schumpeterian quality-ladder framework, in which…

As training artificial intelligence (AI) models is a lengthy and hence costly process, leakage of such a model's internal parameters is highly undesirable. In the case of AI accelerators, side-channel information leakage opens up the threat…

Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…

This paper presents a novel approach to enhance the Binary-Addition-Tree algorithm (BAT) by integrating incremental learning techniques. BAT, known for its simplicity in development, implementation, and application, is a powerful implicit…

This paper presents efficient algorithms, designed to leverage SIMD for performing Montgomery reductions and additions on integers larger than 512 bits. The existing algorithms encounter inefficiencies when parallelized using SIMD due to…

With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak…

Generative models are popular tools with a wide range of applications. Nevertheless, it is as vulnerable to adversarial samples as classifiers. The existing attack methods mainly focus on generating adversarial examples by adding…

Artificial intelligence (AI) methods have become critical in scientific applications to help accelerate scientific discovery. Large language models (LLMs) are being considered as a promising approach to address some of the challenging…

This paper presents two attack strategies designed to evade detection in ADMM-based systems by preventing significant changes to the residual during the attacked iteration. While many detection algorithms focus on identifying false data…

State-of-the-art AI systems can be significantly improved without expensive retraining via "post-training enhancements"-techniques applied after initial training like fine-tuning the system to use a web browser. We review recent…

Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…

Deep neural networks (DNNs) are vulnerable to adversarial examples obtained by adding small perturbations to original examples. The added perturbations in existing attacks are mainly determined by the gradient of the loss function with…

Artificial Intelligence (AI) has witnessed remarkable growth, particularly through the proliferation of Deep Neural Networks (DNNs). These powerful models drive technological advancements across various domains. However, to harness their…

What looks like acceleration can be a quiet transfer of burden from the present to the future. Attempts to replace human labor with AI systems are often presented as rational responses to technological progress, but that view is often…

This paper proposes a novel, non-linear collusion attack on digital fingerprinting systems. The attack is proposed for fingerprinting systems with finite alphabet but can be extended to continuous alphabet. We analyze the error probability…

In recent years, deep neural networks demonstrated state-of-the-art performance in a large variety of tasks and therefore have been adopted in many applications. On the other hand, the latest studies revealed that neural networks are…

Adversarial attacks pose a severe risk to AI systems used in healthcare, capable of misleading models into dangerous misclassifications that can delay treatments or cause misdiagnoses. These attacks, often imperceptible to human perception,…

Quantum modular adders are one of the most fundamental yet versatile quantum computation operations. They help implement functions of higher complexity, such as subtraction and multiplication, which are used in applications such as quantum…

Today's PCs can directly manipulate numbers not longer than 64 bits because the size of the CPU registers and the data-path are limited. Consequently, arithmetic operations such as addition, can only be performed on numbers of that length.…

Specialized accelerators have recently garnered attention as a method to reduce the power consumption of neural network inference. A promising category of accelerators utilizes nonvolatile memory arrays to both store weights and perform…