paper-with-me

Papers

Semantic-Preserving Adversarial Code Comprehension

2022-09-12 · COLING 2022 10 · Yiyang Li, Hongqiu Wu, Hai Zhao

Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against adversarial attacks. However, they have to compromise on the trade-off between the two aspects and none of them consider improving both sides in an effective and practical way. To fill this gap, we propose Semantic-Preserving Adversarial Code Embeddings (SPACE) to find the worst-case semantic-preserving attacks while forcing the model to predict the correct labels under these worst cases. Experiments and analysis demonstrate that SPACE can stay robust against state-of-the-art attacks while boosting the performance of PrLMs for code.

📄 PDF Abstract BibTeX arXiv:2209.05130

Code (1)

ericlee8/space 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Semantically Equivalent Adversarial Rules for Debugging NLP models

2018-07-01 · ACL 2018 7 · Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin

Complex machine learning models for NLP are often brittle, making different predictions for input instances that are extremely similar semantically. To automatically detect this behavior for individual instances, we pres…

Data AugmentationQuestion AnsweringReading ComprehensionSentiment Analysis+2

Preserving Semantics in Textual Adversarial Attacks

2022-11-08 · David Herel, Hugo Cisneros, Tomas Mikolov

The growth of hateful online content, or hate speech, has been associated with a global increase in violent crimes against minorities [23]. Harmful online content can be produced easily, automatically and anonymously. Ev…

Adversarial AttackSentenceSentence EmbeddingSentence-Embedding

Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models

2024-01-25 · Erik Arakelyan, Zhaoqi Liu, Isabelle Augenstein

Recent studies of the emergent capabilities of transformer-based Natural Language Understanding (NLU) models have indicated that they have an understanding of lexical and compositional semantics. We provide evidence that…

Conditional Text GenerationNatural Language InferenceNatural Language UnderstandingSensitivity+1

Semantics-Preserving Adversarial Training

2020-09-23 · Wonseok Lee, Hanbit Lee, Sang-goo Lee

Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this paper, we identify an overlooked problem of …

Adversarial Robustness

How Accurately Do Large Language Models Understand Code?

2025-04-06 · Sabaat Haroon, Ahmad Faraz Khan, Ahmad Humayun, Waris Gill 외

Large Language Models (LLMs) are increasingly used in post-development tasks such as code repair and testing. A key factor in these tasks' success is the model's deep understanding of code. However, the extent to which L…

Code GenerationCode RepairFault localization