An official website of the United States government
Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks, which poses a critical problem. These attacks target LLMs applications through using carefully designed input prompts to divert the model from adhering to original instruction, thereby it could execute unintended actions. These manipulations pose serious security threats which potentially results in data leaks, biased outputs, or harmful responses. This project explores the security vulnerabilities in relation to prompt injection attacks. To detect whether a prompt is vulnerable or not, we follows two approaches: 1) a pre-trained LLM, and 2) a fine-tuned LLM. Then, we conduct a thorough analysis and comparison of the classification performance. Firstly, we use pre-trained XLMRoBERTa model to detect prompt injections using test dataset without any fine-tuning and evaluate it by zero-shot classification. Then, this proposed work will apply supervised fine-tuning to this pre-trained LLM using a task-specific labeled dataset from deep set in huggingface, and this fine-tuned model achieves impressive results with 99.13% accuracy, 100% precision, 98.33% recall and 99.15% F1-score thorough rigorous experimentation and evaluation. We observe that our approach is highly efficient in detecting prompt injection attacks.
more »
« less
Pairing Security Advisories with Vulnerable Functions Using Open-Source LLMs
As the reliance on open-source software dependencies increases, managing the security vulnerabilities in these dependencies becomes complex. State-of-the-art industry tools use reachability analysis of code to alert developers when security vulnerabilities in dependencies are likely to impact their projects. These tools heavily rely on precisely identifying the location of the vulnerability within the dependency, specifically vulnerable functions. However, the process of identifying vulnerable functions is currently either manual or uses a naive automated approach that falsely assumes all changed functions in a security patch link are vulnerable. In this paper, we explore using open-source large language models (LLMs) to improve pairing security advisories with vulnerable functions. We explore various prompting strategies, learning paradigms (i.e., zero-shot vs. few-shot), and show our approach generalizes to other open-source LLMs. Compared to the naive automated approach, we show a 173% increase in precision while only having an 18% decrease in recall. The significant increase in precision to enhance vulnerable function identification lays the groundwork for downstream techniques that depend on this critical information for security analysis and threat mitigation.
more »
« less
- PAR ID:
- 10516056
- Publisher / Repository:
- Springer-Verlag
- Date Published:
- Journal Name:
- Proceedings of the Conference on Detection of Intrusions and Malware & Vulnerability Assessment (DIMVA)
- Subject(s) / Keyword(s):
- Vulnerable Function Security Advisory Security Database Large Language Model
- Format(s):
- Medium: X
- Location:
- Lausanne, Switzerland
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Software depends on upstream projects that regularly fix vulnerabilities, but the documentation of those vulnerabilities is often unreliable or unavailable. Automating the collection of existing vulnerability fixes is essential for downstream projects to reliably update their dependencies due to the sheer number of dependencies in modern software. Prior efforts rely solely on incomplete databases or imprecise or inaccurate statistical analysis of upstream repositories. In this paper, we introduce Differential Alert Analysis (DAA) to discover vulnerability fixes in software projects. In contrast to statistical analysis, DAA leverages static analysis security testing (SAST) tools, which reason over code context and semantics. We provide a language-independent implementation of DAA and show that for Python and Java based projects, DAA has high precision for a ground-truth dataset of vulnerability fixes — even with noisy and low-precision SAST tools. We then use DAA in two large-scale empirical studies covering several prominent ecosystems, finding hundreds of resolved alerts, including many never publicly disclosed. DAA thus provides a powerful, accurate primitive for software projects, code analysis tools, vulnerability databases, and researchers to characterize and enhance the security of software supply chains.more » « less
-
The growing market of the mobile application is overtaking the web application. Mobile application development environment is open source, which attracts new inexperienced developers to gain hands on experience with application development. However, the security of data and vulnerable coding practice is an issue. Among all mobile Operating systems such as, iOS (by Apple), Android (by Google) and Blackberry (RIM), Android dominates the market. The majority of malicious mobile attacks take advantage of vulnerabilities in mobile applications, such as sensitive data leakage via the inadvertent or side channel, unsecured sensitive data storage, data transition and many others. Most of these vulnerabilities can be detected during mobile application analysis phase. In this paper, we explore vulnerability detection for static and dynamic analysis tools. We also suggest limitations of the tools and future directions such as the development of new plugins.more » « less
-
Hardware security verification in hardware design has been identified as a significant bottleneck due to complexity and time-to-market constraints. Assertion-Based Verification is a recognized solution to this challenge; however, assertion generation relies on expertise and labor. While LLMs show promise as automated tools, existing approaches often rely on complex prompt engineering, requiring expert validation. The challenge lies in identifying effective methods for constructing training datasets that enhance LLMs' hardware performance. We introduce HADA (Hardware Assertion through Data Augmentation), a novel framework to train hardware debug specific expert LLM by leveraging its ability to integrate knowledge from formal verification tools, hardware security knowledge database, and version control system. Our results demonstrate that integrating multi-source data significantly enhances the effectiveness of hardware security verification, with each addressing the limitations of the others.more » « less
-
Recent high-profile incidents in open-source software have greatly raised practitioner attention on software supply chain attacks. To guard against potential malicious package updates, security practitioners advocatepinningdependency to specific versions rather thanfloatingin version ranges. However, it remains controversial whether pinning carries a meaningful security benefit that outweighs the cost of maintaining outdated and possibly vulnerable dependencies. In this paper, we quantify, through counterfactual analysis and simulations, the security and maintenance impact of version constraints in the npm ecosystem. By simulating dependency resolutions over historical time points, we find that pinning direct dependencies not only (as expected) increases the cost of maintaining vulnerable and outdated dependencies, but also (surprisingly) even increases the risk of exposure to malicious package updates in larger dependency graphs due to the specifics of npm’s dependency resolution mechanism. Finally, we explore collective pinning strategies to secure the ecosystem against supply chain attacks, suggesting specific changes to npm to enable such interventions. Our study provides guidance for practitioners and tool designers to manage their supply chains more securely.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
