Limin Jia

Chi Zhang, Zifan Wang, Ravi Mangal et al.

Modern large language models (LLMs), such as ChatGPT, have demonstrated impressive capabilities for coding tasks including writing and reasoning about code. They improve upon previous neural network models of code, such as code2seq or seq2seq, that already demonstrated competitive results when performing tasks such as code summarization and identifying code vulnerabilities. However, these previous code models were shown vulnerable to adversarial examples, i.e. small syntactic perturbations that do not change the program's semantics, such as the inclusion of "dead code" through false conditions or the addition of inconsequential print statements, designed to "fool" the models. LLMs can also be vulnerable to the same adversarial perturbations but a detailed study on this concern has been lacking so far. In this paper we aim to investigate the effect of adversarial perturbations on coding tasks with LLMs. In particular, we study the transferability of adversarial examples, generated through white-box attacks on smaller code models, to LLMs. Furthermore, to make the LLMs more robust against such adversaries without incurring the cost of retraining, we propose prompt-based defenses that involve modifying the prompt to include additional information such as examples of adversarially perturbed code and explicit instructions for reversing adversarial perturbations. Our experiments show that adversarial examples obtained with a smaller code model are indeed transferable, weakening the LLMs' performance. The proposed defenses show promise in improving the model's resilience, paving the way to more robust defensive solutions for LLMs in code-related applications.

Ronghao Ni, Mihai Christodorescu, Limin Jia

The rapidly evolving Node$.$js ecosystem currently includes millions of packages and is a critical part of modern software supply chains, making vulnerability detection of Node$.$js packages increasingly important. However, traditional program analysis struggles in this setting because of dynamic JavaScript features and the large number of package dependencies. Recent advances in large language models (LLMs) and the emerging paradigm of LLM-based agents offer an alternative to handcrafted program models. This raises the question of whether an LLM-centric, tool-augmented approach can effectively detect and confirm taint-style vulnerabilities (e.g., arbitrary command injection) in Node$.$js packages. We implement LLMVD$.$js, a multi-stage agent pipeline to scan code, propose vulnerabilities, generate proof-of-concept exploits, and validate them through lightweight execution oracles; and systematically evaluate its effectiveness in taint-style vulnerability detection and confirmation in Node$.$js packages without dedicated static/dynamic analysis engines for path derivation. For packages from public benchmarks, LLMVD$.$js confirms 84% of the vulnerabilities, compared to less than 22% for prior program analysis tools. It also outperforms a prior LLM-program-analysis hybrid approach while requiring neither vulnerability annotations nor prior vulnerability reports. When evaluated on a set of 260 recently released packages (without vulnerability groundtruth information), traditional tools produce validated exploits for few ($\leq 2$) packages, while LLMVD$.$js generates validated exploits for 36 packages.

Md Abdul Hannan, Ronghao Ni, Chi Zhang et al.

Large language models (LLMs) have demonstrated impressive capabilities for many coding tasks, including summarization, translation, completion, and code generation. However, detecting code vulnerabilities remains a challenging task for LLMs. An effective way to improve LLM performance is in-context learning (ICL) - providing few-shot examples similar to the query, along with correct answers, can improve an LLM's ability to generate correct solutions. However, choosing the few-shot examples appropriately is crucial to improving model performance. In this paper, we explore two criteria for choosing few-shot examples for ICL used in the code vulnerability detection task. The first criterion considers if the LLM (consistently) makes a mistake or not on a sample with the intuition that LLM performance on a sample is informative about its usefulness as a few-shot example. The other criterion considers similarity of the examples with the program under query and chooses few-shot examples based on the $k$-nearest neighbors to the given sample. We perform evaluations to determine the benefits of these criteria individually as well as under various combinations, using open-source models on multiple datasets.

Kaiyuan Li, Maverick Woo, Limin Jia

When a software transformation or software security task needs to analyze a given program binary, the first step is often disassembly. Since many modern disassemblers have become highly accurate on many binaries, we believe reliable disassembler benchmarking requires standardizing the set of binaries used and the disassembly ground truth about these binaries. This paper presents (i) a first version of our work-in-progress disassembly benchmark suite, which comprises 879 binaries from diverse projects compiled with multiple compilers and optimization settings, and (ii) a novel disassembly ground truth generator leveraging the notion of "listing files", which has broad support by Clang, GCC, ICC, and MSVC. In additional, it presents our evaluation of four prominent open-source disassemblers using this benchmark suite and a custom evaluation system. Our entire system and all generated data are maintained openly on GitHub to encourage community adoption.

Ronghao Ni, Aidan Z. H. Yang, Min-Chien Hsu et al.

Program analysis tools often produce large volumes of candidate vulnerability reports that require costly manual review, creating a practical challenge: how can security analysts prioritize the reports most likely to be true vulnerabilities? This paper investigates whether machine learning can be applied to prioritizing vulnerabilities reported by program analysis tools. We focus on Node.js packages and collect a benchmark of 1,883 Node.js packages, each containing one reported ACE or ACI vulnerability. We evaluate a variety of machine learning approaches, including classical models, graph neural networks (GNNs), large language models (LLMs), and hybrid models that combine GNN and LLMs, trained on data based on a dynamic program analysis tool's output. The top LLM achieves $F_{1} {=} 0.915$, while the best GNN and classical ML models reaching $F_{1} {=} 0.904$. At a less than 7% false-negative rate, the leading model eliminates 66.9% of benign packages from manual review, taking around 60 ms per package. If the best model is tuned to operate at a precision level of 0.8 (i.e., allowing 20% false positives amongst all warnings), our approach can detect 99.2% of exploitable taint flows while missing only 0.8%, demonstrating strong potential for real-world vulnerability triage.

Gabriel Ferreira, Limin Jia, Joshua Sunshine et al.

The large amount of third-party packages available in fast-moving software ecosystems, such as Node.js/npm, enables attackers to compromise applications by pushing malicious updates to their package dependencies. Studying the npm repository, we observed that many packages in the npm repository that are used in Node.js applications perform only simple computations and do not need access to filesystem or network APIs. This offers the opportunity to enforce least-privilege design per package, protecting applications and package dependencies from malicious updates. We propose a lightweight permission system that protects Node.js applications by enforcing package permissions at runtime. We discuss the design space of solutions and show that our system makes a large number of packages much harder to be exploited, almost for free.

Darion Cassel, Yan Huang, Limin Jia

Programmers of cryptographic applications written in C need to avoid common mistakes such as sending private data over public channels, modifying trusted data with untrusted functions, or improperly ordering protocol steps. These secrecy, integrity, and sequencing policies can be cumbersome to check with existing general-purpose tools. We have developed a novel means of specifying and uncovering violations of these policies that allows for a much lighter-weight approach than previous tools. We embed the policy annotations in C's type system via a source-to-source translation and leverage existing C compilers to check for policy violations, achieving high performance and scalability. We show through case studies of recent cryptographic libraries and applications that our work is able to express detailed policies for large bodies of C code and can find subtle policy violations. To gain formal understanding of our policy annotations, we show formal connections between the policy annotations and an information flow type system and prove a noninterference guarantee.

Omar Chowdhury, Deepak Garg, Limin Jia et al.

Motivated by the problem of simultaneously preserving confidentiality and usability of data outsourced to third-party clouds, we present two different database encryption schemes that largely hide data but reveal enough information to support a wide-range of relational queries. We provide a security definition for database encryption that captures confidentiality based on a notion of equivalence of databases from the adversary's perspective. As a specific application, we adapt an existing algorithm for finding violations of privacy policies to run on logs encrypted under our schemes and observe low to moderate overheads.

Limin Jia, Shayak Sen, Deepak Garg et al.

Security-sensitive applications that execute untrusted code often check the code's integrity by comparing its syntax to a known good value or sandbox the code to contain its effects. System M is a new program logic for reasoning about such security-sensitive applications. System M extends Hoare Type Theory (HTT) to trace safety properties and, additionally, contains two new reasoning principles. First, its type system internalizes logical equality, facilitating reasoning about applications that check code integrity. Second, a confinement rule assigns an effect type to a computation based solely on knowledge of the computation's sandbox. We prove the soundness of system M relative to a step-indexed trace-based semantic model. We illustrate both new reasoning principles of system M by verifying the main integrity property of the design of Memoir, a previously proposed trusted computing system for ensuring state continuity of isolated security-sensitive applications.