Related papers: CoTDeceptor:Adversarial Code Obfuscation Against C…

As large language models (LLMs) are increasingly adopted for code vulnerability detection, their reliability and robustness across diverse vulnerability types have become a pressing concern. In traditional adversarial settings, code…

Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…

The integration of large language models (LLMs) into various pipelines is increasingly widespread, effectively automating many manual tasks and often surpassing human capabilities. Cybersecurity researchers and practitioners have recognised…

Large Language Models (LLMs) have emerged as promising tools for malware detection by analyzing code semantics, identifying vulnerabilities, and adapting to evolving threats. However, their reliability under adversarial compiler-level…

Software obfuscation and encryption present persistent challenges for program comprehension and security analysis, particularly when adversaries conceal Indicators of Compromise (IoCs) such as IP addresses within source code. While Large…

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety.…

With the advancement of Large Language Models (LLMs), significant progress has been made in code generation, enabling LLMs to transform natural language into programming code. These Code LLMs have been widely accepted by massive users and…

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and…

Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD). We introduce ConceptCoder, a fine-tuning method that…

Recent studies have demonstrated outstanding capabilities of large language models (LLMs) in software engineering tasks, including code generation and comprehension. While LLMs have shown significant potential in assisting with coding, LLMs…

With the rapid development of Large Language Models (LLMs), their powerful code-generation capabilities have been widely applied in tasks like code completion and automated development, demonstrating the value of improving coding…

Security code review is a time-consuming and labor-intensive process typically requiring integration with automated security defect detection tools. However, existing security analysis tools struggle with poor generalization, high false…

While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized…

Adversarial smart contracts, mostly on EVM-compatible chains like Ethereum and BSC, are deployed as EVM bytecode to exploit vulnerable smart contracts for financial gain. Detecting such malicious contracts at the time of deployment is an…

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly…

Deep learning-based approaches, particularly those leveraging pre-trained language models (PLMs), have shown promise in automated software vulnerability detection. However, existing methods are predominantly limited to specific programming…

Chain-of-Thought (CoT) enhances an LLM's ability to perform complex reasoning tasks, but it also introduces new security issues. In this work, we present ShadowCoT, a novel backdoor attack framework that targets the internal reasoning…

Large Language Models (LLMs) are increasingly vulnerable to adversarial attacks that can subtly manipulate their outputs. While various defense mechanisms have been proposed, many operate as black boxes, lacking transparency in their…

Dead code introduces several challenges in software development, such as increased binary size and maintenance difficulties. It can also obscure logical errors and be exploited for obfuscation in malware. For LLM-based code-related tasks,…

Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent…