相关论文: Backdooring Neural Code Search

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already…

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…

Neural networks have achieved state-of-the-art performance in solving many problems, including many applications in safety/security-critical systems. Researchers also discovered multiple security issues associated with neural networks. One…

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

Backdoor learning has become an emerging research area towards building a trustworthy machine learning system. While a lot of works have studied the hidden danger of backdoor attacks in image or text classification, there is a limited…

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is…

Reimplementing solutions to previously solved software engineering problems is not only inefficient but also introduces inadequate and error-prone code. Many existing methods achieve impressive performance on this issue by using…

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

Consider the case where a programmer has written some part of a program, but has left part of the program (such as a method or a function body) incomplete. The goal is to use the context surrounding the missing code to automatically 'figure…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for…

Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This enables input samples…

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been…

Neural code models (NCMs) have demonstrated extraordinary capabilities in code intelligence tasks. Meanwhile, the security of NCMs and NCMs-based systems has garnered increasing attention. In particular, NCMs are often trained on…

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…