Understanding multi-turn toxic behaviors in open-domain chatbots

B Chen, G Wang, H Guo, Y Wang, Q Yan - Proceedings of the 26th …, 2023 - dl.acm.org
Recent advances in natural language processing and machine learning have led to the
development of chatbot models, such as ChatGPT, that can engage in conversational …

Multi-turn hidden backdoor in large language model-powered chatbot models

B Chen, N Ivanov, G Wang, Q Yan - Proceedings of the 19th ACM Asia …, 2024 - dl.acm.org
Large Language Model (LLM)-powered chatbot services like GPTs, simulating human-to-
human conversation via machine-generated text, are used in numerous fields. They are …

Federated threat detection for smart home iot rules

G Wang, Q Yan - International Workshop on Federated Learning for …, 2023 - openreview.net
Smart homes are enhanced with the convenience offered by Internet of Things (IoT) devices.
However, the interconnected behaviors of devices can lead to unexpected interactions …

FedPrime: An Adaptive Critical Learning Periods Control Framework for Efficient Federated Learning in Heterogeneity Scenarios

H Du, Z Yang - Joint European Conference on Machine Learning and …, 2024 - Springer
Federated learning (FL) is an emerging distributed optimization paradigm that learns from
data samples distributed across many clients with data privacy protection in the artificial …

AMFL: Asynchronous Multi-level Federated Learning with Client Selection

X Li, Y Zhao, C Qiao - 2024 IEEE/CIC International Conference …, 2024 - ieeexplore.ieee.org
Synchronous Federated Learning (FL) may suffer from increased training time and costs. To
address this issue, Asynchronous Federated Learning (AFL) has been proposed …

Fuzzy-Based Client Selection for Enhanced Model Convergence in Federated Learning

Y Zhou, R Bao - 2024 6th International Conference on …, 2024 - ieeexplore.ieee.org
Federated learning enables the collaborative training of a global model while allowing the
data of multiple clients to remain local. This characteristic renders federated learning highly …

Data-Centric AI for Interaction Security and Privacy in the Internet-of-Things

G Wang - 2024 - search.proquest.com
In the realm of the Internet of Things (IoT), users, devices, and environments communicate
and interact with each other, creating a web of complex interactions. This interconnected …