Rafiqul Islam Rabin

Rafiqul Rabin, Jesse Hostetler, Sean McGregor et al.

While large language models (LLMs) are powerful assistants in programming tasks, they may also produce malicious code. Testing LLM-generated code therefore poses significant risks to assessment infrastructure tasked with executing untrusted code. To address these risks, this work focuses on evaluating the security and confidentiality properties of test environments, reducing the risk that LLM-generated code may compromise the assessment infrastructure. We introduce SandboxEval, a test suite featuring manually crafted test cases that simulate real-world safety scenarios for LLM assessment environments in the context of untrusted code execution. The suite evaluates vulnerabilities to sensitive information exposure, filesystem manipulation, external communication, and other potentially dangerous operations in the course of assessment activity. We demonstrate the utility of SandboxEval by deploying it on an open-source implementation of Dyff, an established AI assessment framework used to evaluate the safety of LLMs at scale. We show, first, that the test suite accurately describes limitations placed on an LLM operating under instructions to generate malicious code. Second, we show that the test results provide valuable insights for developers seeking to harden assessment infrastructure and identify risks associated with LLM execution activities.

Rafiqul Rabin, Sean McGregor, Nick Judd

This paper explores the risk that a large language model (LLM) trained for code generation on data mined from software repositories will generate content that discloses sensitive information included in its training data. We decompose this risk, known in the literature as ``unintended memorization,'' into two components: unintentional disclosure (where an LLM presents secrets to users without the user seeking them out) and malicious disclosure (where an LLM presents secrets to an attacker equipped with partial knowledge of the training data). We observe that while existing work mostly anticipates malicious disclosure, unintentional disclosure is also a concern. We describe methods to assess unintentional and malicious disclosure risks side-by-side across different releases of training datasets and models. We demonstrate these methods through an independent assessment of the Open Language Model (OLMo) family of models and its Dolma training datasets. Our results show, first, that changes in data source and processing are associated with substantial changes in unintended memorization risk; second, that the same set of operational changes may increase one risk while mitigating another; and, third, that the risk of disclosing sensitive information varies not only by prompt strategies or test datasets but also by the types of sensitive information. These contributions rely on data mining to enable greater privacy and security testing required for the LLM training data supply chain.

Md Rafiqul Islam Rabin, Mohammad Amin Alipour

The correctness of compilers is instrumental in the safety and reliability of other software systems, as bugs in compilers can produce executables that do not reflect the intent of programmers. Such errors are difficult to identify and debug. Random test program generators are commonly used in testing compilers, and they have been effective in uncovering bugs. However, the problem of guiding these test generators to produce test programs that are more likely to find bugs remains challenging. In this paper, we use the code snippets in the bug reports to guide the test generation. The main idea of this work is to extract insights from the bug reports about the language features that are more prone to inadequate implementation and using the insights to guide the test generators. We use the GCC C compiler to evaluate the effectiveness of this approach. In particular, we first cluster the test programs in the GCC bugs reports based on their features. We then use the centroids of the clusters to compute configurations for Csmith, a popular test generator for C compilers. We evaluated this approach on eight versions of GCC and found that our approach provides higher coverage and triggers more miscompilation failures than the state-of-the-art test generation techniques for GCC.

Md Rafiqul Islam Rabin, Arjun Mukherjee, Omprakash Gnawali et al.

Source code representations are key in applying machine learning techniques for processing and analyzing programs. A popular approach in representing source code is neural source code embeddings that represents programs with high-dimensional vectors computed by training deep neural networks on a large volume of programs. Although successful, there is little known about the contents of these vectors and their characteristics. In this paper, we present our preliminary results towards better understanding the contents of code2vec neural source code embeddings. In particular, in a small case study, we use the code2vec embeddings to create binary SVM classifiers and compare their performance with the handcrafted features. Our results suggest that the handcrafted features can perform very close to the highly-dimensional code2vec embeddings, and the information gains are more evenly distributed in the code2vec embeddings compared to the handcrafted features. We also find that the code2vec embeddings are more resilient to the removal of dimensions with low information gains than the handcrafted features. We hope our results serve a stepping stone toward principled analysis and evaluation of these code representations.

Md Rafiqul Islam Rabin, Nghi D. Q. Bui, Ke Wang et al.

With the prevalence of publicly available source code repositories to train deep neural network models, neural program models can do well in source code analysis tasks such as predicting method names in given programs that cannot be easily done by traditional program analysis techniques. Although such neural program models have been tested on various existing datasets, the extent to which they generalize to unforeseen source code is largely unknown. Since it is very challenging to test neural program models on all unforeseen programs, in this paper, we propose to evaluate the generalizability of neural program models with respect to semantic-preserving transformations: a generalizable neural program model should perform equally well on programs that are of the same semantics but of different lexical appearances and syntactical structures. We compare the results of various neural program models for the method name prediction task on programs before and after automated semantic-preserving transformations. We use three Java datasets of different sizes and three state-of-the-art neural network models for code, namely code2vec, code2seq, and GGNN, to build nine such neural program models for evaluation. Our results show that even with small semantically preserving changes to the programs, these neural program models often fail to generalize their performance. Our results also suggest that neural program models based on data and control dependencies in programs generalize better than neural program models based only on abstract syntax trees. On the positive side, we observe that as the size of the training dataset grows and diversifies the generalizability of correct predictions produced by the neural program models can be improved too. Our results on the generalizability of neural program models provide insights to measure their limitations and provide a stepping stone for their improvement.

Md Rafiqul Islam Rabin, Ke Wang, Mohammad Amin Alipour

Deep neural networks have been increasingly used in software engineering and program analysis tasks. They usually take a program and make some predictions about it, e.g., bug prediction. We call these models neural program analyzers. The reliability of neural programs can impact the reliability of the encompassing analyses. In this paper, we describe our ongoing efforts to develop effective techniques for testing neural programs. We discuss the challenges involved in developing such tools and our future plans. In our preliminary experiment on a neural model recently proposed in the literature, we found that the model is very brittle, and simple perturbations in the input can cause the model to make mistakes in its prediction.