2 papers
cs.CL2026
Gradually Excavating External Knowledge for Implicit Complex Question Answering
Chang Liu, Xiaoguang Li, Lifeng Shang +4
Recently, large language models (LLMs) have gained much attention for the emergence of human-comparable capabilities and huge potential. However, for open-domain implicit question-…
cs.CV2024
Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers
Binxiao Huang, Jason Chun Lok, Chang Liu +1
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 embedd…