Visual prompting for adversarial robustness
In this work, we leverage visual prompting (VP) to improve adversarial robustness of a fixed,
pre-trained model at test time. Compared to conventional adversarial defenses, VP allows …
pre-trained model at test time. Compared to conventional adversarial defenses, VP allows …
Robustness, security, privacy, explainability, efficiency, and usability of large language models for code
Large language models for code (LLM4Code), which demonstrate strong performance (eg,
high accuracy) in processing source code, have significantly transformed software …
high accuracy) in processing source code, have significantly transformed software …
Adversarial attacks on code models with discriminative graph patterns
Pre-trained language models of code are now widely used in various software engineering
tasks such as code generation, code completion, vulnerability detection, etc. This, in turn …
tasks such as code generation, code completion, vulnerability detection, etc. This, in turn …
Assessing and Improving Syntactic Adversarial Robustness of Pre-trained Models for Code Translation
Context: Pre-trained models (PTMs) have demonstrated significant potential in automatic
code translation. However, the vulnerability of these models in translation tasks, particularly …
code translation. However, the vulnerability of these models in translation tasks, particularly …
A systematic literature review on the impact of AI models on the security of code generation
C Negri-Ribalta, R Geraud-Stewart, A Sergeeva… - Frontiers in Big …, 2024 - frontiersin.org
Introduction Artificial Intelligence (AI) is increasingly used as a helper to develop computing
programs. While it can boost software development and improve coding proficiency, this …
programs. While it can boost software development and improve coding proficiency, this …
On-the-fly improving performance of deep code models via input denoising
Deep learning has been widely adopted to tackle various code-based tasks by building
deep code models based on a large amount of code snippets. While these deep code …
deep code models based on a large amount of code snippets. While these deep code …
Coca: Improving and Explaining Graph Neural Network-Based Vulnerability Detection Systems
Recently, Graph Neural Network (GNN)-based vulnerability detection systems have
achieved remarkable success. However, the lack of explainability poses a critical challenge …
achieved remarkable success. However, the lack of explainability poses a critical challenge …
Exploiting the Adversarial Example Vulnerability of Transfer Learning of Source Code
State-of-the-art source code classification models exhibit excellent task transferability, in
which the source code encoders are first pre-trained on a source domain dataset in a self …
which the source code encoders are first pre-trained on a source domain dataset in a self …
Measuring model alignment for code clone detection using causal interpretation
S Abid, X Cai, L Jiang - Empirical Software Engineering, 2025 - Springer
Abstract Deep Neural Network-based models have demonstrated high accuracy for
semantic code clone detection. However, the lack of generalization poses a threat to the …
semantic code clone detection. However, the lack of generalization poses a threat to the …
Mutual Learning-Based Framework for Enhancing Robustness of Code Models via Adversarial Training
Deep code models (DCMs) have achieved impressive accomplishments and have been
widely applied to various code-related tasks. However, existing studies show that some …
widely applied to various code-related tasks. However, existing studies show that some …