Related papers: Sealing The Backdoor: Unlearning Adversarial Text …

Knowledge distillation has become a cornerstone in modern machine learning systems, celebrated for its ability to transfer knowledge from a large, complex teacher model to a more efficient student model. Traditionally, this process is…

Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks--most notably backdoor attacks. Existing KD…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior…

Self-Supervised Learning (SSL) has become a prominent paradigm for pre-training encoders to learning general-purpose representations from unlabeled data and releasing them on third-party platforms for broad downstream deep learning tasks.…

Text-to-image diffusion models are increasingly vulnerable to backdoor attacks, where malicious modifications to the training data cause the model to generate unintended outputs when specific triggers are present. While classification…

Dataset distillation offers a potential means to enhance data efficiency in deep learning. Recent studies have shown its ability to counteract backdoor risks present in original training samples. In this study, we delve into the theoretical…

Knowledge distillation (KD) is a vital technique for deploying deep neural networks (DNNs) on resource-constrained devices by transferring knowledge from large teacher models to lightweight student models. While teacher models from…

Deep neural networks (DNNs) are known vulnerable to backdoor attacks, a training time attack that injects a trigger pattern into a small proportion of training data so as to control the model's prediction at the test time. Backdoor attacks…

Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation. This paper…

Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…

While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-trained text encoders…

We investigate whether knowledge distillation (KD) from multiple heterogeneous teacher models can enhance the generation of transferable adversarial examples. A lightweight student model is trained using two KD strategies: curriculum-based…

Text generation is of particular interest in many NLP applications such as machine translation, language modeling, and text summarization. Generative adversarial networks (GANs) achieved a remarkable success in high quality image generation…

Distillation via sampling reasoning traces exposes closed-source frontier models to adversarial third parties who can bypass their guardrails and misappropriate their capabilities. Antidistillation methods aim to address this by poisoning…

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of model architecture to…

Due to the prosperity of Artificial Intelligence (AI) techniques, more and more backdoors are designed by adversaries to attack Deep Neural Networks (DNNs).Although the state-of-the-art method Neural Attention Distillation (NAD) can…

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model…

Federated Learning (FL) is a novel framework of decentralized machine learning. Due to the decentralized feature of FL, it is vulnerable to adversarial attacks in the training procedure, e.g. , backdoor attacks. A backdoor attack aims to…