Related papers: TrojanedCM: A Repository of Trojaned Large Languag…
Large language models (LLMs) have become integral to various real-world applications, leveraging massive, web-sourced datasets like Common Crawl, C4, and FineWeb for pretraining. While these datasets provide linguistic data essential for…
Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers which force the network to produce a specific output on any input which includes the trigger. With the increasing relevance of deep…
The Large Language Models (LLMs) have demonstrated great potential in code-related tasks. However, most research focuses on improving the output quality of LLMs (e.g., correctness), and less attention has been paid to the LLM input (e.g.,…
Vulnerability detection is garnering increasing attention in software engineering, since code vulnerabilities possibly pose significant security. Recently, reusing various code pre-trained models has become common for code embedding without…
Code reuse is common in modern software development, but it can also spread vulnerabilities when developers unknowingly copy risky code. The code fragments that preserve the logic of known vulnerabilities are known as vulnerable code clones…
In recent years, the application of large language models (LLMs) to code-related tasks has gained significant attention. However, existing evaluation benchmarks often focus on limited scenarios, such as code generation or completion, which…
Since the rise of neural natural-language-to-code models (NL->Code) that can generate long expressions and statements rather than a single next-token, one of the major problems has been reliably evaluating their generated output. In this…
The rapid development of large language models has revolutionized code intelligence in software development. However, the predominance of closed-source models has restricted extensive research and development. To address this, we introduce…
As large language models (LLMs) become integrated into sensitive workflows, concerns grow over their potential to leak confidential information. We propose TrojanStego, a novel threat model in which an adversary fine-tunes an LLM to embed…
Text classification models, especially neural networks based models, have reached very high accuracy on many popular benchmark datasets. Yet, such models when deployed in real world applications, tend to perform badly. The primary reason is…
Large Language Models (LLMs) applied to code-related applications have emerged as a prominent field, attracting significant interest from both academia and industry. However, as new and improved LLMs are developed, existing evaluation…
Large Language Models (LLMs) offer powerful capabilities in text generation and are increasingly adopted across a wide range of domains. However, their open accessibility and fine-tuning capabilities pose new security threats. This advance…
Programmers often reuse code from source code repositories to reduce the development effort. Code clones are candidates for reuse in exploratory or rapid development, as they represent often repeated functionality in software systems. To…
Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…
The integration of Large Language Models (LLMs) in K--12 education offers both transformative opportunities and emerging risks. This study explores how students may Trojanize prompts to elicit unsafe or unintended outputs from LLMs,…
Quantum computing introduces unfamiliar security vulnerabilities demanding customized threat models. Hardware and software Trojans pose serious concerns needing rethinking from classical paradigms. This paper develops the first structured…
Code cloning, the duplication of code fragments, is common in software development. While some reuse aids productivity, excessive cloning hurts maintainability and introduces bugs. Hence, automatic code clone detection is vital. Meanwhile,…
Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training costs. However, the security implications of this widely-adopted practice remain critically…
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been…
Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that…