Related papers: UltraClean: A Simple Framework to Train Robust Neu…

Backdoor attacks pose a critical threat to machine learning models, causing them to behave normally on clean data but misclassify poisoned data into a poisoned class. Existing defenses often attempt to identify and remove backdoor neurons…

The generalization bound is a crucial theoretical tool for assessing the generalizability of learning methods and there exist vast literatures on generalizability of normal learning, adversarial learning, and data poisoning. Unlike other…

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

With the development of deep learning (DL), DL-based code search models have achieved state-of-the-art performance and have been widely used by developers during software development. However, the security issue, e.g., recommending…

The huge supporting training data on the Internet has been a key factor in the success of deep learning models. However, this abundance of public-available data also raises concerns about the unauthorized exploitation of datasets for…

Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep neural networks are vulnerable to backdoor attacks. By…

Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural…

Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and…

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. A trojaned neural network behaves normally with clean inputs. However, if the input contains a particular trigger, the…

As deep neural networks (DNNs) are growing larger, their requirements for computational resources become huge, which makes outsourcing training more popular. Training in a third-party platform, however, may introduce potential risks that a…

Recent studies have highlighted the vulnerability of deep neural networks to backdoor attacks, where models are manipulated to rely on embedded triggers within poisoned samples, despite the presence of both benign and trigger information.…

Recent studies have revealed the vulnerability of Deep Neural Network (DNN) models to backdoor attacks. However, existing backdoor attacks arbitrarily set the trigger mask or use a randomly selected trigger, which restricts the…

Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and…

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Deep Neural Networks (DNN) are becoming increasingly more important in assisted and automated driving. Using such entities which are obtained using machine learning is inevitable: tasks such as recognizing traffic signs cannot be developed…

Natural language processing (NLP) models are known to be vulnerable to backdoor attacks, which poses a newly arisen threat to NLP models. Prior online backdoor defense methods for NLP models only focus on the anomalies at either the input…

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger patterns or objects (e.g., stickers, sunglasses, etc.). We find…