相关论文: Excess Capacity and Backdoor Poisoning

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from…

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Extensive literature on backdoor poison attacks has studied attacks and defenses for backdoors using "digital trigger patterns." In contrast, "physical backdoors" use physical objects as triggers, have only recently been identified, and are…

The rapid development of deep learning has benefited from the release of some high-quality open-sourced datasets ($e.g.$, ImageNet), which allows researchers to easily verify the effectiveness of their algorithms. Almost all existing…

In this paper, we study PAC learnability and certification of predictions under instance-targeted poisoning attacks, where the adversary who knows the test instance may change a fraction of the training set with the goal of fooling the…

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…

Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the learned model. While recent work has proposed a number of…

Contrastive learning pre-trains an image encoder using a large amount of unlabeled data such that the image encoder can be used as a general-purpose feature extractor for various downstream tasks. In this work, we propose PoisonedEncoder, a…

In recent years, data poisoning attacks have been increasingly designed to appear harmless and even beneficial, often with the intention of verifying dataset ownership or safeguarding private data from unauthorized use. However, these…

Predictions of certifiably robust classifiers remain constant in a neighborhood of a point, making them resilient to test-time attacks with a guarantee. In this work, we present a previously unrecognized threat to robust machine learning…

With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. The majority of the work in algorithmic fairness focus on assessing and improving the…

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model…

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…

Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim classifier will predict to an attacker-desired target class whenever a test sample is embedded with the same backdoor pattern (BP) that was used to…

Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversary-specified labels while maintaining performance on clean…

Under a commonly-studied backdoor poisoning attack against classification models, an attacker adds a small trigger to a subset of the training data, such that the presence of this trigger at test time causes the classifier to always predict…