5 citations · 12 across the 6 of their papers we have counts for
6 papers
Efficient and Secure Sleepy Model for BFT Consensus
Pengkun Ren, Hai Dong, Zahir Tari +1
Byzantine Fault Tolerant (BFT) consensus protocols for dynamically available systems face a critical challenge: balancing latency and security in fluctuating node participation. Ex…
RITFIS: Robust input testing framework for LLMs-based intelligent software
Mingxuan Xiao, Yan Xiao, Hai Dong +2
The dependence of Natural Language Processing (NLP) intelligent software on Large Language Models (LLMs) is increasingly prominent, underscoring the necessity for robustness testin…
LEAP: Efficient and Automated Test Method for NLP Software
Mingxuan Xiao, Yan Xiao, Hai Dong +2
The widespread adoption of DNNs in NLP software has highlighted the need for robustness. Researchers proposed various automatic testing techniques for adversarial test cases. Howev…
Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound
Hanbo Cai, Pengcheng Zhang, Hai Dong +3
Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models a…
VSVC: Backdoor attack against Keyword Spotting based on Voiceprint Selection and Voice Conversion
Hanbo Cai, Pengcheng Zhang, Hai Dong +2
Keyword spotting (KWS) based on deep neural networks (DNNs) has achieved massive success in voice control scenarios. However, training of such DNN-based KWS systems often requires…
PBSM: Backdoor attack against Keyword spotting based on pitch boosting and sound masking
Hanbo Cai, Pengcheng Zhang, Hai Dong +2
Keyword spotting (KWS) has been widely used in various speech control scenarios. The training of KWS is usually based on deep neural networks and requires a large amount of data. M…