Adversarial Robustness for Code
Machine learning and deep learning in particular has been recently used to successfully address many tasks in the domain of code such as finding and fixing bugs, code completion, decompilation, type inference and many others. However, the issue of adversarial robustness of models for code has gone largely unnoticed. In this work, we explore this issue by: (i) instantiating adversarial attacks for code (a domain with discrete and highly structured inputs), (ii) showing that, similar to other domains, neural models for code are vulnerable to adversarial attacks, and (iii) combining existing and novel techniques to improve robustness while preserving high accuracy.
Code (1)
Tasks
Adversarial RobustnessBIG-bench Machine LearningCode CompletionSimilar Papers 제목 키워드 기반
Revisiting Role of Autoencoders in Adversarial Settings
To combat against adversarial attacks, autoencoder structure is widely used to perform denoising which is regarded as gradient masking. In this paper, we revisit the role of autoencoders in adversarial settings. Through …
Adversarial DefenseAdversarial RobustnessDenoisingLanguage-Driven Anchors for Zero-Shot Adversarial Robustness
Deep Neural Networks (DNNs) are known to be susceptible to adversarial attacks. Previous researches mainly focus on improving adversarial robustness in the fully supervised setting, leaving the challenging domain of zero…
Adversarial DefenseAdversarial RobustnessImage ClassificationZero-Shot Image Classification+1On the Adversarial Robustness of Generative Autoencoders in the Latent Space
The generative autoencoders, such as the variational autoencoders or the adversarial autoencoders, have achieved great success in lots of real-world applications, including image generation, and signal communication. How…
Adversarial Robustnesscompressed sensingDecoderDisentanglement+1CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent studies propose to finetune the vision enco…
Adversarial RobustnessImage-text matchingText MatchingCLAWSAT: Towards Both Robust and Accurate Code Models
We integrate contrastive learning (CL) with adversarial learning to co-optimize the robustness and accuracy of code models. Different from existing works, we show that code obfuscation, a standard code transformation ope…
Code GenerationCode SummarizationContrastive LearningSelf-Supervised Learning