相关论文: Invisible Clean-Label Backdoor Attacks for Generat…

Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations…

Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversarially fine-tunes pre-trained LMs to amplify the exposure of…

Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research. Training generative adversarial neural networks (GAN) usually requires large amounts of training…

Machine learning techniques help to understand patterns of a dataset to create a defense mechanism against cyber attacks. However, it is difficult to construct a theoretical model due to the imbalances in the dataset for discriminating…

Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual…

Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research and augment medical datasets. Training generative adversarial neural networks (GANs) usually…

Federated learning, while being a promising approach for collaborative model training, is susceptible to backdoor attacks due to its decentralized nature. Backdoor attacks have shown remarkable stealthiness, as they compromise model…

Despite significant advancements, large language models (LLMs) still struggle with providing accurate answers when lacking domain-specific or up-to-date knowledge. Retrieval-Augmented Generation (RAG) addresses this limitation by…

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

Machine learning (ML) models used in medical imaging diagnostics can be vulnerable to a variety of privacy attacks, including membership inference attacks, that lead to violations of regulations governing the use of medical data and…

Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security threats associated…

Membership inference attacks (MIAs) are critical tools for assessing privacy risks and ensuring compliance with regulations like the General Data Protection Regulation (GDPR). However, their potential for auditing unauthorized use of data…

Quality control is a crucial activity performed by manufacturing companies to ensure their products conform to the requirements and specifications. The introduction of artificial intelligence models enables to automate the visual quality…

Currently, large models are prone to generating harmful content when faced with complex attack instructions, significantly reducing their defensive capabilities. To address this issue, this paper proposes a method based on constructing data…

Machine learning driven object detection and classification within non-visible imagery has an important role in many fields such as night vision, all-weather surveillance and aviation security. However, such applications often suffer due to…

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can…

Out-of-distribution generalization can be categorized into two types: common perturbations arising from natural variations in the real world and adversarial perturbations that are intentionally crafted to deceive neural networks. While deep…

Since the training data of the target model is not available in the black-box substitute attack, most recent schemes utilize GANs to generate data for training the substitute model. However, these GANs-based schemes suffer from low training…