Related papers: Mask and Restore: Blind Backdoor Defense at Test T…

To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data. This practice is widely regarded as secure,…

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Deep learning models have been shown to be vulnerable to recent backdoor attacks. A backdoored model behaves normally for inputs containing no attacker-secretly-chosen trigger and maliciously for inputs with the trigger. To date, backdoor…

Backdoor attacks on language models pose a significant threat to AI safety, where models behave normally on most inputs but exhibit harmful behavior when triggered by specific patterns. Detecting such backdoors through mechanistic…

Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised…

Neural code models (NCMs) have been widely used to address various code understanding tasks, such as defect detection. However, numerous recent studies reveal that such models are vulnerable to backdoor attacks. Backdoored NCMs function…

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…

Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by…

In this work, we examine the impact of inter-patch dependencies in the decoder of masked autoencoders (MAE) on representation learning. We decompose the decoding mechanism for masked reconstruction into self-attention between mask tokens…

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently,…

Deep neural networks (DNNs) deployed in a cloud often allow users to query models via the APIs. However, these APIs expose the models to model extraction attacks (MEAs). In this attack, the attacker attempts to duplicate the target model by…

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

In recent years, deep learning-based Monocular Depth Estimation (MDE) models have been widely applied in fields such as autonomous driving and robotics. However, their vulnerability to backdoor attacks remains unexplored. To fill the gap in…

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…

The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…

Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the…

According to recent studies, the vulnerability of state-of-the-art Neural Networks to adversarial input samples has increased drastically. A neural network is an intermediate path or technique by which a computer learns to perform tasks…

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual…

Medical foundation models are gaining prominence in the medical community for their ability to derive general representations from extensive collections of medical image-text pairs. Recent research indicates that these models are…