Related papers: CRUST-Bench: A Comprehensive Benchmark for C-to-sa…

Rust is a modern systems programming language that ensures memory safety by enforcing ownership and borrowing rules at compile time. While the unsafe keyword allows programmers to bypass these restrictions, it introduces significant risks.…

This paper presents a system combining symbolic execution (KLEE) with a 4-agent multi-LLM architecture for detecting memory vulnerabilities in Rust unsafe code. A central challenge we address is the incomplete-code problem: CVE database…

Code completion, a highly valuable topic in the software development domain, has been increasingly promoted for use by recent advances in large language models (LLMs). To date, visible LLM-based code completion frameworks such as GitHub…

Performance of clustering algorithms is evaluated with the help of accuracy metrics. There is a great diversity of clustering algorithms, which are key components of many data analysis and exploration systems. However, there exist only few…

Accurate confidence estimation is essential for trustworthy large language models (LLMs) systems, as it empowers the user to determine when to trust outputs and enables reliable deployment in safety-critical applications. Current confidence…

C-rusted is an innovative technology whereby C programs can be (partly) annotated so as to express: ownership, exclusivity and shareability of language, system and user-defined resources; dynamic properties of objects and the way they…

The advancement of large language models has intensified the need to modernize enterprise applications and migrate legacy systems to secure, versatile languages. However, existing code translation benchmarks primarily focus on individual…

Memory safety violations in low-level code, written in languages like C, continues to remain one of the major sources of software vulnerabilities. One method of removing such violations by construction is to port C code to a safe C dialect.…

Large Language Models have demonstrated exceptional proficiency on coding tasks, but it is challenging to precisely evaluate their code reasoning ability. Existing benchmarks are insufficient as they are unrealistic and conflate semantic…

Large language models (LLMs) show promise in code translation due to their ability to generate idiomatic code. However, a significant limitation when using LLMs for code translation is scalability: existing works have shown a drop in…

AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmarks that are challenging, but more crucially, directly…

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal,…

Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. However, the continual learning aspect of these aligned LLMs has been largely overlooked. Existing…

As large language models (LLMs) become integral to safety-critical applications, ensuring their robustness against adversarial prompts is paramount. However, existing red teaming datasets suffer from inconsistent risk categorizations,…

This paper explores the use of Large Language Models (LLMs) to automate the generation of test skeletons -- structural templates that outline unit test coverage without implementing full test logic. Test skeletons are especially important…

How can one build a feature-rich, general-purpose, Rust-based operating system (OS) with a minimal and sound Trusted Computing Base (TCB) for memory safety? Existing Rust-based OSes fall short due to their improper use of unsafe Rust in…

We introduce a novel validation framework to measure the true robustness of learning models for real-world applications by creating source-inclusive and source-exclusive partitions in a dataset via clustering. We develop a robustness metric…

Large Language Models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Recently, many tool-use benchmark datasets have been proposed. However, existing…

Large Language Models (LLMs) have shown great promise in vulnerability identification. As C/C++ comprises half of the Open-Source Software (OSS) vulnerabilities over the past decade and updates in OSS mainly occur through commits, enhancing…

Whereas contemporary Error Correcting Codes (ECC) designs occupy a significant fraction of total die area in chip-multiprocessors (CMPs), approaches to deal with the vulnerability increase of CMP architecture against Single Event Upsets…