Related papers: MGC: A Compiler Framework Exploiting Compositional…

Malware detectors based on machine learning (ML) have been shown to be susceptible to adversarial malware examples. However, current methods to generate adversarial malware examples still have their limits. They either rely on detailed…

Large Language Models (LLMs) are increasingly being used as security engineering tools to summarize and explain malware behavior to analysts. A common assumption is that Retrieval-Augmented Generation (RAG) improves explanation quality by…

Code decompilation analysis is a fundamental yet challenging task in malware reverse engineering, particularly due to the pervasive use of sophisticated obfuscation techniques. Although recent large language models (LLMs) have shown promise…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Large Language Models (LLMs) have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and…

Large Language Models (LLMs) have demonstrated remarkable capabilities in code-related tasks, raising concerns about their potential for automated exploit generation (AEG). This paper presents the first systematic study on LLMs'…

This paper introduces an innovative approach that combines Large Language Models (LLMs) with Formal Verification strategies for automatic software vulnerability repair. Initially, we employ Bounded Model Checking (BMC) to identify…

Large Language Models (LLMs) such as ChatGPT and GitHub Copilot have revolutionized automated code generation in software engineering. However, as these models are increasingly utilized for software development, concerns have arisen…

Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…

Current compiler optimization reports often present complex, technical information that is difficult for programmers to interpret and act upon effectively. This paper assesses the capability of large language models (LLM) to understand…

The code generation capabilities of large language models(LLMs) have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely overlooked the security risks inherent in the generated code.…

As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level vulnerabilities with real-world impact. This paper studies how adversarial attacks…

While pre-trained multimodal representations (e.g., CLIP) have shown impressive capabilities, they exhibit significant compositional vulnerabilities leading to counterintuitive judgments. We introduce Multimodal Adversarial Compositionality…

Rapid progress in generative AI has given rise to Compound AI systems - pipelines comprised of multiple large language models (LLM), software tools and database systems. Compound AI systems are constructed on a layered traditional software…

Large language models (LLMs) have emerged as powerful tools for many AI problems and exhibit remarkable in-context learning (ICL) capabilities. Compositional ability, solving unseen complex tasks that combine two or more simple tasks, is an…

Large Language Model (LLM) alignment aims to ensure that LLM outputs match with human values. Researchers have demonstrated the severity of alignment problems with a large spectrum of jailbreak techniques that can induce LLMs to produce…

With the growing pace of using Deep Learning (DL) to solve various problems, securing these models against adversaries has become one of the main concerns of researchers. Recent studies have shown that DL-based malware detectors are…

Large language models (LLMs) have the potential to revolutionize how we design and implement compilers and code translation tools. However, existing LLMs struggle to handle long and complex programs. We introduce LEGO-Compiler, a novel…

Malicious software attacks are having an increasingly significant economic impact. Commercial malware detection software can be costly, and tools that attribute malware to the specific software vulnerabilities it exploits are largely…

With the recent advancement of Large Language Models (LLMs), generating functionally correct code has become less complicated for a wide array of developers. While using LLMs has sped up the functional development process, it poses a heavy…