6 papers
Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks
Yi Yang, Xiaoke Chen, Jinyang Huang +6
Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few…
Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget
Yi Yang, Jinyang Huang, Binbin Liu +5
Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigg…
Multi-Stage Evolutionary Model Merging with Meta Data Driven Curriculum Learning for Sentiment-Specialized Large Language Modeling
Keito Inoshita, Xiaokang Zhou, Akira Kawai
The emergence of large language models (LLMs) has significantly transformed natural language processing (NLP), enabling more generalized models to perform various tasks with minima…
CIEGAD: Cluster-Conditioned Interpolative and Extrapolative Framework for Geometry-Aware and Domain-Aligned Data Augmentation
Keito Inoshita, Xiaokang Zhou, Akira Kawai +1
In practical deep learning deployment, the scarcity of data and the imbalance of label distributions often lead to semantically uncovered regions within the real-world data distrib…
A Near-Optimal Category Information Sampling in RFID Systems
Xiujun Wang, Zhi Liu, Xiaokang Zhou +4
In many RFID-enabled applications, objects are classified into different categories, and the information associated with each object's category (called category information) is wri…
Inputs for the measurements from BESIII
Xiaokang Zhou
The CKM angle is important for testing the unitarity of the CKM matrix and searching for new physics. can be extracted by the interference between and i…