Search Results for author:
Found 49 papers, 32 papers with code
DIRECT : A Transformer-based Model for Decompiled Identifier Renaming
Decompiling binary executables to high-level code is an important step in reverse engineering scenarios, such as malware analysis and legacy code maintenance.
Vulnerability Detection with Code Language Models: How Far Are We?
Evaluating code LMs on PrimeVul reveals that existing benchmarks significantly overestimate the performance of these models.
CYCLE: Learning to Self-Refine the Code Generation
Pre-trained code language models have achieved promising performance in code generation and improved the programming efficiency of human developers.
PropTest: Automatic Property Testing for Improved Visual Programming
Visual Programming has emerged as an alternative to end-to-end black-box visual reasoning models.
Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM
Recent works using large language models (LLMs) for test generation have focused on improving generation quality through optimizing the test generation context and correcting errors in model outputs, but use fixed prompting strategies that prompt the model to generate tests without additional guidance.
Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
In this paper, we first formally define the self-consistency of Code LLMs and then design a framework, IdentityChain, which effectively and efficiently evaluates the self-consistency and conventional accuracy of a model at the same time.
Towards Causal Deep Learning for Vulnerability Detection
Our results show that CausalVul consistently improved the model accuracy, robustness and OOD performance for all the state-of-the-art models and datasets we experimented.
Language-Guided Traffic Simulation via Scene-Level Diffusion
Realistic and controllable traffic simulation is a core capability that is necessary to accelerate autonomous vehicle (AV) development.
A Static Evaluation of Code Completion by Large Language Models
Large language models trained on code have shown great potential to increase productivity of software developers.
Variation of Gender Biases in Visual Recognition Models Before and After Finetuning
We also find that (2) models finetuned on larger scale datasets are more likely to introduce new biased associations.
Greener yet Powerful: Taming Large Code Generation Models with Quantization
Such large models incur significant resource usage (in terms of memory, latency, and dollars) as well as carbon footprint.
On ML-Based Program Translation: Perils and Promises
In the future, we envision an end-to-end program translation tool where programming domain knowledge can be embedded into an ML-based translation pipeline using pre- and post-processing steps.
ReCode: Robustness Evaluation of Code Generation Models
Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation.
Guided Conditional Diffusion for Controllable Traffic Simulation
Controllable and realistic traffic simulation is critical for developing and verifying autonomous vehicles.
Multi-lingual Evaluation of Code Generation Models
Using these benchmarks, we are able to assess the performance of code generation models in a multi-lingual fashion, and discovered generalization ability of language models on out-of-domain languages, advantages of multi-lingual models over mono-lingual, the ability of few-shot prompting to teach the model new languages, and zero-shot translation abilities even on mono-lingual settings.
NeuDep: Neural Binary Memory Dependence Analysis
Notably, NeuDep also outperforms the current state-of-the-art on these tasks.
ContraCLM: Contrastive Learning For Causal Language Model
Specifically, we attain $44\%$ relative improvement on the Semantic Textual Similarity tasks and $34\%$ on Code-to-Code Search tasks.
NatGen: Generative pre-training by "Naturalizing" source code
Pre-trained Generative Language models (e. g. PLBART, CodeT5, SPT-Code) for source code yielded strong results on several tasks in the past few years, including code generation and translation.
Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages
In code generation, the model learns to do the opposite.
Repairing Group-Level Errors for DNNs Using Weighted Regularization
In particular, it can repair confusion error and bias error of DNN models for both single-label and multi-label image classifications.
Unicorn: Reasoning about Configurable System Performance through the lens of Causality
Understanding and reasoning about the performance behavior of highly configurable systems, over a vast and variable space, is challenging.
VELVET: a noVel Ensemble Learning approach to automatically locate VulnErable sTatements
Automatically locating vulnerable statements in source code is crucial to assure software security and alleviate developers' debugging efforts.
A Survey on Scenario-Based Testing for Automated Driving Systems in High-Fidelity Simulation
To bridge this gap, in this work, we provide a generic formulation of scenario-based testing in high-fidelity simulation and conduct a literature review on the existing works.
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts
We pre-train our model with a much smaller dataset, the size of which is only 5% of the state-of-the-art models' training datasets, to illustrate the effectiveness of our data augmentation and the pre-training approach.
Detecting Multi-Sensor Fusion Errors in Advanced Driver-Assistance Systems
We define the failures (e. g., car crashes) caused by the faulty MSF as fusion errors and develop a novel evolutionary-based domain-specific search framework, FusED, for the efficient detection of fusion errors.
Neural Network Guided Evolutionary Fuzzing for Finding Traffic Violations of Autonomous Vehicles
Self-driving cars and trucks, autonomous vehicles (AVs), should not be accepted by regulatory bodies and the public until they have much higher confidence in their safety and reliability -- which can most practically and convincingly be achieved by testing.
Retrieval Augmented Code Generation and Summarization
To mimic developers' code or summary generation behavior, we propose a retrieval augmented framework, REDCODER, that retrieves relevant code or summaries from a retrieval database and provides them as a supplement to code generation or summarization models.
Ranked #1 on
Code Generation
on CodeXGLUE - CodeSearchNet
(using extra training data)
On Multi-Modal Learning of Editing Source Code
With in-depth investigation and analysis, we show that developers' hint as an input modality can narrow the search space for patches and outperform state-of-the-art models to generate correctly patched code in top-1 position.
Unified Pre-training for Program Understanding and Generation
Experiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models.
Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity
We thus train the model to learn execution semantics from the functions' micro-traces, without any manual labeling effort.
Understanding Local Robustness of Deep Neural Networks under Natural Variations
To this end, we study the local per-input robustness properties of the DNNs and leverage those properties to build a white-box (DeepRobust-W) and a black-box (DeepRobust-B) tool to automatically identify the non-robust points.
Deep Learning & Software Engineering: State of Research and Future Directions
The intent of this report is to serve as a potential roadmap to guide future work that sits at the intersection of SE & DL.
Deep Learning based Vulnerability Detection: Are We There Yet?
In this paper, we ask, "how well do the state-of-the-art DL-based techniques perform in a real-world vulnerability prediction scenario?".
Software Engineering
Patching as Translation: the Data and the Metaphor
Given these findings, we demonstrate how a more principled approach to model design, based on our empirical findings and general knowledge of software development, can lead to better solutions.
Multitask Learning Strengthens Adversarial Robustness
Although deep networks achieve strong accuracy on a range of computer vision benchmarks, they remain vulnerable to adversarial attacks, where imperceptible input perturbations fool the network.
MTFuzz: Fuzzing with a Multi-Task Neural Network
The compact embedding can be used to guide the mutation process effectively by focusing most of the mutations on the parts of the embedding where the gradient is high.
Software Engineering
Pythia: Grammar-Based Fuzzing of REST APIs with Coverage-guided Feedback and Learning-based Mutations
This paper introduces Pythia, the first fuzzer that augments grammar-based fuzzing with coverage-guided feedback and a learning-based mutation strategy for stateful REST API fuzzing.
A Transformer-based Approach for Source Code Summarization
Generating a readable summary that describes the functionality of a program is known as source code summarization.
ConEx: Efficient Exploration of Big-Data System Configurations for Better Performance
For cost reduction, we developed and experimentally tested and validated two approaches: using scaled-up big data jobs as proxies for the objective function for larger jobs and using a dynamic job similarity measure to infer that results obtained for one kind of big data problem will work well for similar problems.
AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
Due to the inherent robustness of segmentation models, traditional norm-bounded attack methods show limited effect on such type of models.
Metric Learning for Adversarial Robustness
Deep networks are well-known to be fragile to adversarial attacks.
Neutaint: Efficient Dynamic Taint Analysis with Neural Networks
Dynamic taint analysis (DTA) is widely used by various applications to track information flow during runtime execution.
Cryptography and Security
Testing DNN Image Classifiers for Confusion & Bias Errors
We found that many of the reported erroneous cases in popular DNN image classifiers occur because the trained models confuse one class with another or show biases towards some classes over others.
Tree2Tree Neural Translation Model for Learning Source Code Changes
Our evaluation shows the effectiveness of CODIT in learning and suggesting abstract change templates.
Software Engineering
A Case Study on the Impact of Similarity Measure on Information Retrieval based Software Engineering Tasks
In particular, we analyze two previously proposed tools for project recommendation and bug localization tasks, which leverage diverse software artifacts, and observe that an informed choice of similarity measure indeed leads to improved performance of the existing SE tools.
NEUZZ: Efficient Fuzzing with Neural Program Smoothing
However, even state-of-the-art fuzzers are not very efficient at finding hard-to-trigger software bugs.
Obfuscation Resilient Search through Executable Classification
It is challenging to search for executables relevant to an obfuscated application for developers to analyze efficiently.
Software Engineering Cryptography and Security
Building Language Models for Text with Named Entities
Text in many domains involves a significant amount of named entities.
Ranked #1 on
Recipe Generation
on Now You're Cooking!
DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars
Most existing testing techniques for DNN-driven vehicles are heavily dependent on the manual collection of test data under different driving conditions which become prohibitively expensive as the number of test conditions increases.
