Zobrazeno 1 - 10
of 174
pro vyhledávání: '"Jia, Jinyuan"'
Eye gaze contains rich information about human attention and cognitive processes. This capability makes the underlying technology, known as gaze tracking, a critical enabler for many ubiquitous applications and has triggered the development of easy-t
Externí odkaz:
http://arxiv.org/abs/2408.00950
Federated graph learning (FedGL) is an emerging federated learning (FL) framework that extends FL to learn graph data from diverse sources. FL for non-graph data has shown to be vulnerable to backdoor attacks, which inject a shared backdoor trigger i
Externí odkaz:
http://arxiv.org/abs/2407.08935
Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns and has been widely deployed in industry. However, watermarking is v
Externí odkaz:
http://arxiv.org/abs/2407.04086
Explainable Graph Neural Network (GNN) has emerged recently to foster the trust of using GNNs. Existing GNN explainers are developed from various perspectives to enhance the explanation performance. We take the first step to study GNN explainers unde
Externí odkaz:
http://arxiv.org/abs/2406.03193
The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, within which any perturbation does not alter the original input's classific
Externí odkaz:
http://arxiv.org/abs/2406.00699
In Federated Learning (FL), a set of clients collaboratively train a machine learning model (called global model) without sharing their local training data. The local training data of clients is typically non-i.i.d. and heterogeneous, resulting in va
Externí odkaz:
http://arxiv.org/abs/2405.20975
Autor:
Nie, Yuzhou., Wang, Yanting., Jia, Jinyuan., De Lucia, Michael J., Bastian, Nathaniel D., Guo, Wenbo., Song, Dawn.
One key challenge in backdoor attacks against large foundation models is the resource limits. Backdoor attacks usually require retraining the target model, which is impractical for very large foundation models. Existing backdoor attacks are mainly de
Externí odkaz:
http://arxiv.org/abs/2405.16783
Few-shot classification with foundation models (e.g., CLIP, DINOv2, PaLM-2) enables users to build an accurate classifier with a few labeled training samples (called support samples) for a classification task. However, an attacker could perform data
Externí odkaz:
http://arxiv.org/abs/2404.08631
Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D points, audio, text, etc. Similar to unimodal models, many existing studi
Externí odkaz:
http://arxiv.org/abs/2403.19080
Autor:
Xu, Zhangchen, Jiang, Fengqing, Niu, Luyao, Jia, Jinyuan, Lin, Bill Yuchen, Poovendran, Radha
As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks,
Externí odkaz:
http://arxiv.org/abs/2402.08983