A5092781949- COVID-19 diagnosis using AI
- Advanced Data Processing Techniques
- Topic Modeling
- Blockchain Technology Applications and Security
- Geographic Information Systems Studies
- Spam and Phishing Detection
- Internet Traffic Analysis and Secure E-voting
- Advanced Computational Techniques and Applications
Sichuan University
2023
In real-world scenarios, the number of phishing and benign emails is usually imbalanced, leading to traditional machine learning or deep algorithms being biased towards misclassifying emails. Few studies take measures address imbalance between them, which significantly threatens people’s financial information security. To mitigate impact on model enhance detection performance emails, this paper proposes two new with undersampling: Fisher–Markov-based ensemble (FMPED) method...
As online platforms and recommendation algorithms evolve, people are increasingly trapped in echo chambers, leading to biased understandings of various issues. To combat this issue, we have introduced PerSphere, a benchmark designed facilitate multi-faceted perspective retrieval summarization, thus breaking free from these information silos. For each query within there two opposing claims, supported by distinct, non-overlapping perspectives drawn one or more documents. Our goal is accurately...
Active learning (AL), which aims to construct an effective training set by iteratively curating the most formative unlabeled data for annotation, has been widely used in low-resource tasks. Most active techniques classification rely on model's uncertainty or disagreement choose data, suffering from problem of over-confidence superficial patterns and a lack exploration. Inspired cognitive processes humans deduce predict through causal information, we take initial attempt towards integrating...