arXiv subjects

Mohammad Amin Alipour

Publications and source records attributed to Mohammad Amin Alipour.

At least 19 recordsLinked to original sources

arXiv2025

Capturing the Effects of Quantization on Trojans in Code LLMs

Large language models of code exhibit high capability in performing diverse software engineering tasks, such as code translation, defect detection, text-to-code generation, and code summarization. While their ability to enhance developer productivity has spurred widespread use, these models have also seen substantial growth in size, often reaching billions of parameters. This scale demands efficient memory resource usage, prompting practitioners to use optimization techniques such as model quantization. Quantization uses smaller bit representations for the model parameters, reducing the precision of the weights. In this work, we investigate the impact of quantization on the risk of data poisoning attacks on these models, specifically examining whether it mitigates or exacerbates such vulnerabilities. We focus on two large language models, Meta's Llama-2-7b and CodeLlama-7b, applied to an SQL code generation task. Additionally, we introduce a new metric for measuring trojan signals in compromised models. We find that quantization has differing effects on code-generating LLMs: while reducing precision does not significantly alter Llama-2's behavior, it boosts performance and reduces attack success rates in CodeLlama, particularly at 4-bit precision.

cs.SE↗

arXiv2025

From Prompts to Propositions: A Logic-Based Lens on Student-LLM Interactions

Background and Context. The increasing integration of large language models (LLMs) in computing education presents an emerging challenge in understanding how students use LLMs and craft prompts to solve computational tasks. Prior research has used both qualitative and quantitative methods to analyze prompting behavior, but these approaches lack scalability or fail to effectively capture the semantic evolution of prompts. Objective. In this paper, we investigate whether students prompts can be systematically analyzed using propositional logic constraints. We examine whether this approach can identify patterns in prompt evolution, detect struggling students, and provide insights into effective and ineffective strategies. Method. We introduce Prompt2Constraints, a novel method that translates students prompts into logical constraints. The constraints are able to represent the intent of the prompts in succinct and quantifiable ways. We used this approach to analyze a dataset of 1,872 prompts from 203 students solving introductory programming tasks. Findings. We find that while successful and unsuccessful attempts tend to use a similar number of constraints overall, when students fail, they often modify their prompts more significantly, shifting problem-solving strategies midway. We also identify points where specific interventions could be most helpful to students for refining their prompts. Implications. This work offers a new and scalable way to detect students who struggle in solving natural language programming tasks. This work could be extended to investigate more complex tasks and integrated into programming tools to provide real-time support.

cs.HC↗

arXiv2024

Student-AI Interaction: A Case Study of CS1 students

The new capabilities of generative artificial intelligence tools Generative AI, such as ChatGPT, allow users to interact with the system in intuitive ways, such as simple conversations, and receive (mostly) good-quality answers. These systems can support students' learning objectives by providing accessible explanations and examples even with vague queries. At the same time, they can encourage undesired help-seeking behaviors by providing solutions to the students' homework. Therefore, it is important to better understand how students approach such tools and the potential issues such approaches might present for the learners. In this paper, we present a case study for understanding student-AI collaboration to solve programming tasks in the CS1 introductory programming course. To this end, we recruited a gender-balanced majority non-white set of 15 CS1 students at a large public university in the US. We observed them solving programming tasks. We used a mixed-method approach to study their interactions as they tackled Python programming tasks, focusing on when and why they used ChatGPT for problem-solving. We analyze and classify the questions submitted by the 15 participants to ChatGPT. Additionally, we analyzed user interaction patterns, their reactions to ChatGPT's responses, and the potential impacts of Generative AI on their perception of self-efficacy. Our results suggest that in about a third of the cases, the student attempted to complete the task by submitting the full description of the tasks to ChatGPT without making any effort on their own. We also observed that few students verified their solutions. We discuss the results and their potential implications.

cs.HC↗

arXiv2024

Unlearning Trojans in Large Language Models: A Comparison Between Natural Language and Source Code

This work investigates the application of Machine Unlearning (MU) for mitigating the impact of trojans embedded in conventional large language models of natural language (Text-LLMs) and large language models of code (Code-LLMs) We propose a novel unlearning approach, LYA, that leverages both gradient ascent and elastic weight consolidation, a Fisher Information Matrix (FIM) based regularization technique, to unlearn trojans from poisoned models. We compare the effectiveness of LYA against conventional techniques like fine-tuning, retraining, and vanilla gradient ascent. The subject models we investigate are BERT and CodeBERT, for sentiment analysis and code defect detection tasks, respectively. Our findings demonstrate that the combination of gradient ascent and FIM-based regularization, as done in LYA, outperforms existing methods in removing the trojan's influence from the poisoned model, while preserving its original functionality. To the best of our knowledge, this is the first work that compares and contrasts MU of trojans in LLMs, in the NL and Coding domain.

cs.SE↗

arXiv2024

Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing

Unit testing is crucial in software engineering for ensuring quality. However, it's not widely used in parallel and high-performance computing software, particularly scientific applications, due to their smaller, diverse user base and complex logic. These factors make unit testing challenging and expensive, as it requires specialized knowledge and existing automated tools are often ineffective. To address this, we propose an automated method for generating unit tests for such software, considering their unique features like complex logic and parallel processing. Recently, large language models (LLMs) have shown promise in coding and testing. We explored the capabilities of Davinci (text-davinci-002) and ChatGPT (gpt-3.5-turbo) in creating unit tests for C++ parallel programs. Our results show that LLMs can generate mostly correct and comprehensive unit tests, although they have some limitations, such as repetitive assertions and blank test cases.

cs.SE↗

arXiv2024

Revisiting Human Information Foraging: Adaptations for LLM-based Chatbots

Information Foraging Theory's (IFT) framing of human information seeking choices as decision-theoretic cost-value judgments has successfully explained how people seek information among linked patches of information (e.g., linked webpages). However, the theory has to be adopted and validated in non-patchy LLM-based chatbot environments, before its postulates can be reliably applied to the design of such chat-based information seeking environments. This paper is a thought experiment that applies the IFT cost-value proposition to LLM-based chatbots and presents a set of preliminary hypotheses to guide future theory-building efforts for how people seek information in such environments.

cs.HC↗

arXiv2024

Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into training data, allowing attackers to manipulate the behavior of the model maliciously. In this paper, we focus on analyzing the model parameters to detect potential backdoor signals in code models. Specifically, we examine attention weights and biases, and context embeddings of the clean and poisoned CodeBERT and CodeT5 models. Our results suggest noticeable patterns in context embeddings of poisoned samples for both the poisoned models; however, attention weights and biases do not show any significant differences. This work contributes to ongoing efforts in white-box detection of backdoor signals in LLMs of code through the analysis of parameters and embeddings.

cs.SE↗

arXiv2024

Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy

Large language models (LLMs) have provided a lot of exciting new capabilities in software development. However, the opaque nature of these models makes them difficult to reason about and inspect. Their opacity gives rise to potential security risks, as adversaries can train and deploy compromised models to disrupt the software development process in the victims' organization. This work presents an overview of the current state-of-the-art trojan attacks on large language models of code, with a focus on triggers -- the main design point of trojans -- with the aid of a novel unifying trigger taxonomy framework. We also aim to provide a uniform definition of the fundamental concepts in the area of trojans in Code LLMs. Finally, we draw implications of findings on how code models learn on trigger design.

cs.SE↗

arXiv2024

A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques

In this work, we study literature in Explainable AI and Safe AI to understand poisoning of neural models of code. In order to do so, we first establish a novel taxonomy for Trojan AI for code, and present a new aspect-based classification of triggers in neural models of code. Next, we highlight recent works that help us deepen our conception of how these models understand software code. Then we pick some of the recent, state-of-art poisoning strategies that can be used to manipulate such models. The insights we draw can potentially help to foster future research in the area of Trojan AI for code.

cs.SE↗

arXiv2024

On Trojan Signatures in Large Language Models of Code

Trojan signatures, as described by Fields et al. (2021), are noticeable differences in the distribution of the trojaned class parameters (weights) and the non-trojaned class parameters of the trojaned model, that can be used to detect the trojaned model. Fields et al. (2021) found trojan signatures in computer vision classification tasks with image models, such as, Resnet, WideResnet, Densenet, and VGG. In this paper, we investigate such signatures in the classifier layer parameters of large language models of source code. Our results suggest that trojan signatures could not generalize to LLMs of code. We found that trojaned code models are stubborn, even when the models were poisoned under more explicit settings (finetuned with pre-trained weights frozen). We analyzed nine trojaned models for two binary classification tasks: clone and defect detection. To the best of our knowledge, this is the first work to examine weight-based trojan signature revelation techniques for large-language models of code and furthermore to demonstrate that detecting trojans only from the weights in such models is a hard problem.

cs.CR↗

arXiv2024

Measuring Impacts of Poisoning on Model Parameters and Neuron Activations: A Case Study of Poisoning CodeBERT

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into training data, allowing attackers to manipulate the behavior of the model maliciously. In this paper, we focus on analyzing the model parameters to detect potential backdoor signals in code models. Specifically, we examine attention weights and biases, activation values, and context embeddings of the clean and poisoned CodeBERT models. Our results suggest noticeable patterns in activation values and context embeddings of poisoned samples for the poisoned CodeBERT model; however, attention weights and biases do not show any significant differences. This work contributes to ongoing efforts in white-box detection of backdoor signals in LLMs of code through the analysis of parameters and activations.

cs.SE↗

arXiv2024

Trust in Generative AI among students: An Exploratory Study

Generative artificial systems (GenAI) have experienced exponential growth in the past couple of years. These systems offer exciting capabilities, such as generating programs, that students can well utilize for their learning. Among many dimensions that might affect the effective adoption of GenAI, in this paper, we investigate students' \textit{trust}. Trust in GenAI influences the extent to which students adopt GenAI, in turn affecting their learning. In this study, we surveyed 253 students at two large universities to understand how much they trust \genai tools and their feedback on how GenAI impacts their performance in CS courses. Our results show that students have different levels of trust in GenAI. We also observe different levels of confidence and motivation, highlighting the need for further understanding of factors impacting trust.

cs.HC↗

arXiv2023

TrojanedCM: A Repository of Trojaned Large Language Models of Code

With the rapid growth of research in trojaning deep neural models of source code, we observe that there is a need of developing a benchmark trojaned models for testing various trojan detection and unlearning techniques. In this work, we aim to provide the scientific community with diverse trojaned code models, that cover a variety of state-of-the-art architectures, on which they can examine such techniques. We thus present TrojanedCM, a publicly available repository of clean and poisoned models of source code. We provide poisoned models for two code classification tasks (defect detection and clone detection) and a code generation task (text-to-code generation). We finetuned popular pretrained code models such as CodeBERT, PLBART, CodeT5, CodeT5+, on poisoned datasets that we generated from benchmark datasets (Devign, BigCloneBench, CONCODE) for the above mentioned tasks. The repository also provides full access to the architecture and parameters of the models, allowing practitioners to investigate different white-box analysis techniques. In addition to the poisoned models, we also provide a poisoning framework using which practitioners can deploy various poisoning strategies for the different tasks and models of source code. All the material are accessible via this link: https://github.com/UH-SERG/TrojanedCM.

cs.SE↗

arXiv2023

Occlusion-based Detection of Trojan-triggering Inputs in Large Language Models of Code

Large language models (LLMs) are becoming an integrated part of software development. These models are trained on large datasets for code, where it is hard to verify each data point. Therefore, a potential attack surface can be to inject poisonous data into the training data to make models vulnerable, aka trojaned. It can pose a significant threat by hiding manipulative behaviors inside models, leading to compromising the integrity of the models in downstream tasks. In this paper, we propose an occlusion-based human-in-the-loop technique, OSeql, to distinguish trojan-triggering inputs of code. The technique is based on the observation that trojaned neural models of code rely heavily on the triggering part of input; hence, its removal would change the confidence of the models in their prediction substantially. Our results suggest that OSeql can detect the triggering inputs with almost 100% recall. We discuss the problem of false positives and how to address them. These results provide a baseline for future studies in this field.

cs.SE↗

arXiv2023

A Study of Variable-Role-based Feature Enrichment in Neural Models of Code

Although deep neural models substantially reduce the overhead of feature engineering, the features readily available in the inputs might significantly impact training cost and the performance of the models. In this paper, we explore the impact of an unsuperivsed feature enrichment approach based on variable roles on the performance of neural models of code. The notion of variable roles (as introduced in the works of Sajaniemi et al. [Refs. 1,2]) has been found to help students' abilities in programming. In this paper, we investigate if this notion would improve the performance of neural models of code. To the best of our knowledge, this is the first work to investigate how Sajaniemi et al.'s concept of variable roles can affect neural models of code. In particular, we enrich a source code dataset by adding the role of individual variables in the dataset programs, and thereby conduct a study on the impact of variable role enrichment in training the Code2Seq model. In addition, we shed light on some challenges and opportunities in feature enrichment for neural code intelligence models.

cs.LG↗

arXiv2023

Study of Distractors in Neural Models of Code

Finding important features that contribute to the prediction of neural models is an active area of research in explainable AI. Neural models are opaque and finding such features sheds light on a better understanding of their predictions. In contrast, in this work, we present an inverse perspective of distractor features: features that cast doubt about the prediction by affecting the model's confidence in its prediction. Understanding distractors provide a complementary view of the features' relevance in the predictions of neural models. In this paper, we apply a reduction-based technique to find distractors and provide our preliminary results of their impacts and types. Our experiments across various tasks, models, and datasets of code reveal that the removal of tokens can have a significant impact on the confidence of models in their predictions and the categories of tokens can also play a vital role in the model's confidence. Our study aims to enhance the transparency of models by emphasizing those tokens that significantly influence the confidence of the models.

cs.LG↗

arXiv2023

Code2Snapshot: Using Code Snapshots for Learning Representations of Source Code

There are several approaches for encoding source code in the input vectors of neural models. These approaches attempt to include various syntactic and semantic features of input programs in their encoding. In this paper, we investigate Code2Snapshot, a novel representation of the source code that is based on the snapshots of input programs. We evaluate several variations of this representation and compare its performance with state-of-the-art representations that utilize the rich syntactic and semantic features of input programs. Our preliminary study on the utility of Code2Snapshot in the code summarization and code classification tasks suggests that simple snapshots of input programs have comparable performance to state-of-the-art representations. Interestingly, obscuring input programs have insignificant impacts on the Code2Snapshot performance, suggesting that, for some tasks, neural models may provide high performance by relying merely on the structure of input programs.

cs.SE↗

arXiv2022

Memorization and Generalization in Neural Code Intelligence Models

Deep Neural Networks (DNNs) are increasingly being used in software engineering and code intelligence tasks. These are powerful tools that are capable of learning highly generalizable patterns from large datasets through millions of parameters. At the same time, their large capacity can render them prone to memorizing data points. Recent work suggests that the memorization risk manifests especially strongly when the training dataset is noisy, involving many ambiguous or questionable samples, and memorization is the only recourse. The goal of this paper is to evaluate and compare the extent of memorization and generalization in neural code intelligence models. It aims to provide insights on how memorization may impact the learning behavior of neural models in code intelligence systems. To observe the extent of memorization in models, we add random noise to the original training dataset and use various metrics to quantify the impact of noise on various aspects of training and testing. We evaluate several state-of-the-art neural code intelligence models and benchmarks based on Java, Python, and Ruby codebases. Our results highlight important risks: millions of trainable parameters allow the neural networks to memorize anything, including noisy data, and provide a false sense of generalization. We observed all models manifest some forms of memorization. This can be potentially troublesome in most code intelligence tasks where they rely on rather noise-prone and repetitive data sources, such as code from GitHub. To the best of our knowledge, we provide the first study to quantify memorization effects in the domain of software engineering and code intelligence systems. This work raises awareness and provides new insights into important issues of training neural models in code intelligence systems that are usually overlooked by software engineering researchers.

cs.LG↗