Related papers: Protecting Model Adaptation from Trojans in the Un…

Poisoning-based backdoor attacks expose vulnerabilities in the data preparation stage of deep neural network (DNN) training. The DNNs trained on the poisoned dataset will be embedded with a backdoor, making them behave well on clean data…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are scarce and unlabeled. While this paradigm has proven effective for improving clean…

Adversarial training (AT) is a robust learning algorithm that can defend against adversarial attacks in the inference phase and mitigate the side effects of corrupted data in the training phase. As such, it has become an indispensable…

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,…

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks. However, this combination of pre-training and downstream adaptation creates an expanded…

With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massive corpora of code mined from unvetted public sources. As a…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

Artificial Intelligence (AI) relies heavily on deep learning - a technology that is becoming increasingly popular in real-life applications of AI, even in the safety-critical and high-risk domains. However, it is recently discovered that…

While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisoning attacks, but these studies placed stricter requirements…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

The increasing adaptation of vision models across domains, such as satellite imagery and medical scans, has raised an emerging privacy risk: models may inadvertently retain and leak sensitive source-domain specific information in the target…

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…

Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is…

Training machine learning models can be very expensive or even unaffordable. This may be, for example, due to data limitations, such as unavailability or being too large, or computational power limitations. Therefore, it is a common…

Unsupervised domain adaptation targets to transfer task-related knowledge from labeled source domain to unlabeled target domain. Although tremendous efforts have been made to minimize domain divergence, most existing methods only partially…

Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from performance…

Pre-trained models (PTMs) are widely adopted across various downstream tasks in the machine learning supply chain. Adopting untrustworthy PTMs introduces significant security risks, where adversaries can poison the model supply chain by…