Related papers: SieveFL: Hierarchical Runtime-Aware Pruning for Sc…

Automating penetration testing is crucial for enhancing cybersecurity, yet current Large Language Models (LLMs) face significant limitations in this domain, including poor error handling, inefficient reasoning, and an inability to perform…

As the number of sensors becomes massive in Internet of Things (IoT) networks, the amount of data is humongous. To process data in real-time while protecting user privacy, federated learning (FL) has been regarded as an enabling technique…

Large Language Models (LLMs) deployed in practical and safety-critical settings are increasingly susceptible to bit-flip faults caused by hardware degradation, cosmic radiation, or deliberate fault-injection attacks such as Rowhammer. These…

Code optimization is a challenging task requiring a substantial level of expertise from developers. Nonetheless, this level of human capacity is not sufficient considering the rapid evolution of new hardware architectures and software…

The current hardware landscape and application scale is driving performance engineers towards writing bespoke optimizations. Verifying such optimizations, and generating minimal failing cases, is important for robustness in the face of…

Code Linting tools are vital for detecting potential defects in Verilog code. However, the limitations of traditional Linting tools are evident in frequent false positives and redundant defect reports. Recent advancements in large language…

Federated Learning (FL) facilitates collaborative model training across distributed clients while ensuring data privacy. Traditionally, FL relies on a centralized server to coordinate learning, which creates bottlenecks and a single point…

Hybrid parallelism underpins large-scale LLM training across tens of thousands of GPUs. At such scale, hardware failures on individual devices lead to performance skew across devices, diminishing overall training efficiency. Existing…

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

Data-flow testing (DFT) aims to detect potential data interaction anomalies by focusing on the points at which variables receive values and the points at which these values are used. Such test objectives are referred as \emph{def-use…

Large Language Models (LLMs) have shown promise in multiple software engineering tasks including code generation, program repair, code summarisation, and test generation. Fault localisation is instrumental in enabling automated debugging…

Data protection across organizations is limiting the application of centralized learning (CL) techniques. Federated learning (FL) enables multiple participants to build a learning model without sharing data. Nevertheless, there are very few…

With the rapid evolution of Large Language Models (LLMs) and their large-scale experimentation in cloud-computing spaces, the challenge of guaranteeing their security and efficiency in a failure scenario has become a main issue. To ensure…

Enterprises want AI code completion that is both high-quality and private, but they face a tension: proprietary models yield better results yet risk exposing proprietary code, while self-hosting large models is expensive and hard to…

While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such…

Software fault prediction (SFP) is a critical task in software engineering, enabling early identification of faults in modules to improve software quality and reduce maintenance costs. This research investigates the combined effects of…

Data selection in instruction tuning emerges as a pivotal process for acquiring high-quality data and training instruction-following large language models (LLMs), but it is still a new and unexplored research area for vision-language models…

Software failures remain a major challenge in modern software development, and identifying the code elements responsible for failures is a time-consuming debugging task. While extensive research has focused on fault localization in the…

Automated Program Repair (APR) has benefited from the code understanding and generation capabilities of Large Language Models (LLMs). Existing feedback-based APR methods iteratively refine candidate patches using test execution feedback and…

Large Language Models (LLMs) have recently achieved strong performance in software code generation. However, applying them to hardware description languages (HDLs), such as Verilog, remains challenging because high-quality training data are…