相关论文: Verification of Embedded Memory Systems using Effi…

Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance of a passage w.r.t. to a query using efficient similarity…

Scan and ring schemes of the pseudo-ring memory selftesting are investigated. Both schemes are based on emulation of the linear or nonlinear feedback shift register by memory itself. Peculiarities of the pseudo-ring schemes implementation…

In this paper, we present VerifyML, the first secure inference framework to check the fairness degree of a given Machine learning (ML) model. VerifyML is generic and is immune to any obstruction by the malicious model holder during the…

We present Porthos, the first tool that discovers porting bugs in performance-critical code. Porthos takes as input a program and the memory models of the source architecture for which the program has been developed and the target model to…

Quantum emulators play an important role in the development and testing of quantum algorithms, especially given the limitations of the current FTQC era. Developing high-speed, memory-optimized quantum emulators is a growing research trend,…

Order Dependencies (ODs) have many applications, such as query optimization, data integration, and data cleaning. Although many works addressed the problem of discovering OD (and its variants), they do not consider datasets with missing…

Hybrid memory systems, comprised of emerging non-volatile memory (NVM) and DRAM, have been proposed to address the growing memory demand of applications. Emerging NVM technologies, such as phase-change memories (PCM), memristor, and 3D…

Smart contracts written in Solidity are programs used in blockchain networks, such as Etherium, for performing transactions. However, as with any piece of software, they are prone to errors and may present vulnerabilities, which malicious…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

In this work, we introduce Erasure of Language Memory (ELM), a principled approach to concept-level unlearning that operates by matching distributions defined by the model's own introspective classification capabilities. Our key insight is…

Matrix multiplication is the dominant computation during Machine Learning (ML) inference. To efficiently perform such multiplication operations, Compute-in-memory (CiM) paradigms have emerged as a highly energy efficient solution. However,…

Verifying whether the machine unlearning process has been properly executed is critical but remains underexplored. Some existing approaches propose unlearning verification methods based on backdooring techniques. However, these methods…

Existing benchmarks are becoming saturated and struggle to separate model performances due to factors like data contamination and advancing LLM capabilities. This paper introduces EMDM (Enhanced Model Differentiation Metric), a novel…

In the field of speaker verification, session or channel variability poses a significant challenge. While many contemporary methods aim to disentangle session information from speaker embeddings, we introduce a novel approach using an…

Algorithmic verification of realistic systems to satisfy safety and other temporal requirements has suffered from poor scalability of the employed formal approaches. To design systems with rigorous guarantees, many approaches still rely on…

Concerned with the reliability of neural networks, researchers have developed verification techniques to prove their robustness. Most verifiers work with real-valued networks. Unfortunately, the exact (complete and sound) verifiers face…

High-Bandwidth Memory (HBM) delivers exceptional bandwidth and energy efficiency for AI workloads, but its high cost per bit, driven in part by stringent on-die reliability requirements, poses a growing barrier to scalable deployment. This…

Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift…

The complexity of digital embedded systems has been increasing in different safety-critical applications such as industrial automation, process control, transportation, and medical digital devices. The correct operation of these systems…

The so-called matrix-element method (MEM) has long been used successfully as a classification tool in particle physics searches. In the presence of invisible final state particles, the traditional MEM typically assigns probabilities to an…