Related papers: Scalable Fingerprinting of Large Language Models

As software grows in complexity to accommodate diverse features and platforms, software bloating has emerged as a significant challenge, adversely affecting performance and security. However, existing approaches inadequately address the…

We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in existing methods, including the limited dataset scale when…

We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs). Our work is motivated by the rapid emergence of numerous new LLM families with distinct architectures and training…

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and…

As cyber threats continue to evolve and diversify, it has become increasingly challenging to identify the root causes of security breaches that occur between periodic security assessments. This paper explores the fundamental importance of…

Software vulnerabilities continue to be ubiquitous, even in the era of AI-powered code assistants, advanced static analysis tools, and the adoption of extensive testing frameworks. It has become apparent that we must not simply prevent…

Large Language Model (LLM) is changing the software development paradigm and has gained huge attention from both academia and industry. Researchers and developers collaboratively explore how to leverage the powerful problem-solving ability…

Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors. Prior work demonstrates that LLMs benefit substantially from structured feedback, static analysis,…

Large language models (LLMs), renowned for their impressive capabilities in various tasks, have significantly advanced artificial intelligence. Yet, these advancements have raised growing concerns about privacy and security implications. To…

Large Language Models (LLMs) are widely used in software engineering (SE) research and practice, yet their non-determinism, opaque training data, and rapidly evolving models threaten the reproducibility and replicability of empirical…

Understanding peptide properties is often assumed to require modeling long-range molecular interactions, motivating the use of complex graph neural networks and pretrained transformers. Yet, whether such long-range dependencies are…

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to…

Code smells are symptoms of potential code quality problems that may affect software maintainability, thus increasing development costs and impacting software reliability. Large language models (LLMs) have shown remarkable capabilities for…

Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their proficiency in various tasks, LLMs like PaLM 540B and Llama-3.1…

Components of machine learning systems are not (yet) perceived as security hotspots. Secure coding practices, such as ensuring that no execution paths depend on confidential inputs, have not yet been adopted by ML developers. We initiate…

Malicious domains are part of the landscape of the internet but are becoming more prevalent and more dangerous to both companies and individuals. They can be hosted on variety of technologies and serve an array of content, ranging from…

In recent years, Large Language Models (LLMs) have made significant strides towards Artificial General Intelligence. However, training these models from scratch requires substantial computational resources and vast amounts of text data. In…

The demand for biometric systems has been increasing with the growth of the smartphone market. Biometric devices allow the user to authenticate easily while securing its private data without the need to remember any access code. Amongst…

A recent watermarking scheme for language models achieves distortion-free embedding and robustness to edit-distance attacks. However, it suffers from limited generation diversity and high detection overhead. In parallel, recent research has…

This paper addresses the growing need for efficient large language models (LLMs) on mobile devices, driven by increasing cloud costs and latency concerns. We focus on designing top-quality LLMs with fewer than a billion parameters, a…