Related papers: Finding Memory Leaks in C/C++ Programs via Neuro-S…

Static analysis plays a crucial role in software vulnerability detection, yet faces a persistent precision-scalability tradeoff. In large codebases like the Linux kernel, traditional static analysis tools often generate excessive false…

Code optimization remains a core objective in software development, yet modern compilers struggle to navigate the enormous optimization spaces. While recent research has looked into employing large language models (LLMs) to optimize source…

Patching severe security flaws in complex software remains a major challenge. While automated tools like fuzzers efficiently discover bugs, fixing deep-rooted low-level faults (e.g., use-after-free and memory corruption) still requires…

Memory safety has long been a critical challenge in software engineering, particularly for legacy systems written in memory-unsafe languages such as C and C++. Rust, one of the youngest modern programming languages, offers built-in…

The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and substantial economic loss. Consequently, robust code vulnerability detection is essential for…

Compilers are complex, and significant effort has been expended on testing them. Techniques such as random program generation and differential testing have proved highly effective and have uncovered thousands of bugs in production…

A compiler bug arises if the behaviour of a compiled concurrent program, as allowed by its architecture memory model, is not a behaviour permitted by the source program under its source model. One might reasonably think that most compiler…

Autonomous Large Language Model (LLM) agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security…

This paper presents AutoHint, a novel framework for automatic prompt engineering and optimization for Large Language Models (LLM). While LLMs have demonstrated remarkable ability in achieving high-quality annotation in various tasks, the…

Programs written in C/C++ often include inline assembly: a snippet of architecture-specific assembly code used to access low-level functionalities that are impossible or expensive to simulate in the source language. Although inline assembly…

Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks, sensitive data passes through inter-agent messages, shared memory, and tool arguments, all pathways…

Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory…

One of the most significant challenges in the field of software code auditing is the presence of vulnerabilities in software source code. Every year, more and more software flaws are discovered, either internally in proprietary code or…

Automated vulnerability detection in critical-infrastructure software confronts a fundamental barrier: industrial software is routinely deployed as stripped, symbol-free binaries that deprive conventional Software Composition Analysis of…

Program analysis is a technique to reason about programs without executing them, and it has various applications in compilers, integrated development environments, and security. In this work, we present a machine learning pipeline that…

In the last three decades, memory safety issues in system programming languages such as C or C++ have been one of the significant sources of security vulnerabilities. However, there exist only a few attempts with limited success to cope…

Memory corruption errors in C/C++ programs remain the most common source of security vulnerabilities in today's systems. Control-flow hijacking attacks exploit memory corruption vulnerabilities to divert program execution away from the…

In C++, objects can be allocated in static memory, on the stack, or on the heap -- the latter being significantly more performance-costly than the former options. We hypothesized that programmers, particularly those involved in widely-used…

Data science pipelines to train and evaluate models with machine learning may contain bugs just like any other code. Leakage between training and test data can lead to overestimating the model's accuracy during offline evaluations, possibly…

Researchers have recently devised tools for debloating software and detecting configuration errors. Several of these tools rely on the observation that programs are composed of an initialization phase followed by a main-computation phase.…