Related papers: Code Generation for Cryptographic Kernels using Mu…

Non-orthogonal multiple access (NOMA) is a promising technology which meets the demands of massive connectivity in future wireless networks. Sparse code multiple access (SCMA) is a popular code-domain NOMA technique. The effectiveness of…

Machine learning (ML) systems that guarantee security and privacy often rely on Fully Homomorphic Encryption (FHE) as a cornerstone technique, enabling computations on encrypted data without exposing sensitive information. However, a…

Pretrained multilingual encoder models can directly perform zero-shot multilingual tasks or linguistic probing by reformulating the input examples into cloze-style prompts. This is accomplished by predicting the probabilities of the label…

Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands. Quantization has emerged as a…

Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities. In this paper, we propose COIN++, a neural compression framework that seamlessly…

Elliptic curve cryptography (ECC) is widely used in security applications such as public key cryptography (PKC) and zero-knowledge proofs (ZKP). ECC is composed of modular arithmetic, where modular multiplication takes most of the…

Homomorphic encryption (HE) enables computation over encrypted data, offering strong privacy guarantees for untrusted computing environments. Practical adoption remains limited by high computational complexity, large ciphertext sizes, and…

Many areas of machine learning and science involve large linear algebra problems, such as eigendecompositions, solving linear systems, computing matrix exponentials, and trace estimation. The matrices involved often have Kronecker,…

We introduce a novel machine learning strategy, kernel addition Gaussian process regression (KA-GPR), in molecular-orbital-based machine learning (MOB-ML) to learn the total correlation energies of general electronic structure theories for…

Sparse Mixture-of-Experts (MoE) models enable efficient scalability by activating only a small sub-set of experts per input, yet their massive parameter counts lead to substantial memory and energy inefficiency during inference. Analog…

We propose a multi-bit leveled fully homomorphic encryption scheme using multivariate polynomial evaluations. The security of the scheme depends on the hardness of the Learning with Errors (LWE) problem. For homomorphic multiplication, the…

The previously introduced Modular Ontology Modeling methodology (MOMo) attempts to mimic the human analogical process by using modular patterns to assemble more complex concepts. To support this, MOMo organizes organizes ontology design…

Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models~(LLMs) to unlock state-of-the-art performance. Fine-tuning approaches…

Using natural language processing (NLP) technologies to develop medical chatbots makes the diagnosis of the patient more convenient and efficient, which is a typical application in healthcare AI. Because of its importance, lots of research…

With the widespread adoption of Large Language Models (LLMs), many deep learning practitioners are looking for strategies of running these models more efficiently. One such strategy is to use sparse Mixture-of-Experts (MoE) - a type of…

We present our perspective and goals on highperformance computing for nanoscience in accordance with the global trend toward "peta-scale computing." After reviewing our results obtained through the grid-enabled version of the fragment…

Homomorphic Encryption (HE) provides strong data privacy for cloud services but at the cost of prohibitive computational overhead. While GPUs have emerged as a practical platform for accelerating HE, there remains an order-of-magnitude…

In this paper we explore several contexts where an adversary has an upper hand over the defender by using special hardware in an attack. These include password processing, hard-drive protection, cryptocurrency mining, resource sharing, code…

Mixed-precision quantization improves the budget--accuracy trade-off for large language models (LLMs) by allocating more bits to sensitive modules. However, automating this allocation at LLM scale faces a unique combination of constraints:…

Cryptographic protocols are used in different environments, but existing methods for protocol analysis focus only on the protocols, without being sensitive to assumptions about their environments. LPA is a tool which analyzes protocols in…