Large language models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across …
Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An adversary can embed a hidden backdoor into a model to manipulate its predictions by only …
Self-supervised learning in computer vision trains on unlabeled data, such as images or (image, text) pairs, to obtain an image encoder that learns high-quality embeddings for input …
Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined …
Backdoors can be injected to NLP models such that they misbehave when the trigger words or sentences appear in an input sample. Detecting such backdoors given only a subject …
Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word …
P Li, P Cheng, F Li, W Du, H Zhao, G Liu - Proceedings of the AAAI …, 2023 - ojs.aaai.org
The huge training overhead, considerable commercial value, and various potential security risks make it urgent to protect the intellectual property (IP) of Deep Neural Networks (DNNs) …
X Qi, T Xie, R Pan, J Zhu, Y Yang… - Proceedings of the …, 2022 - openaccess.thecvf.com
One major goal of the AI security community is to securely and reliably produce and deploy deep learning models for real-world applications. To this end, data poisoning based …