6 papers
Rethinking Molecular Graph Backdoors under Chemistry-aware Admission
Thinh T. H. Nguyen, Sze Jue Yang, Khoa D. Doan +2
Backdoor attacks on molecular graph neural networks (GNNs) are typically evaluated as abstract graph edits, but real molecular learning pipelines do not train on arbitrary graphs.…
Banking Done Right: Redefining Retail Banking with Language-Centric AI
Xin Jie Chua, Jeraelyn Ming Li Tan, Jia Xuan Tan +6
This paper presents Ryt AI, an LLM-native agentic framework that powers Ryt Bank to enable customers to execute core financial transactions through natural language conversation. T…
MyCulture: Exploring Malaysia's Diverse Culture under Low-Resource Language Constraints
Zhong Ken Hew, Jia Xin Low, Sze Jue Yang +1
Large Language Models (LLMs) often exhibit cultural biases due to training data dominated by high-resource languages like English and Chinese. This poses challenges for accurately…
FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning
Tuan Nguyen, Sze Jue Yang, Khoa D. Doan +2
Horizontal federated learning (HFL) backdoor audits often summarize model behavior through clean accuracy (CA), mean attack success rate (ASR), or a single known-trigger test. Such…
Synthesizing Physical Backdoor Datasets: An Automated Framework Leveraging Deep Generative Models
Sze Jue Yang, Chinh D. La, Quang H. Nguyen +4
Backdoor attacks, representing an emerging threat to the integrity of deep neural networks, have garnered significant attention due to their ability to compromise deep learning sys…
Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack
Sze Jue Yang, Quang Nguyen, Chee Seng Chan +1
The vulnerabilities to backdoor attacks have recently threatened the trustworthiness of machine learning models in practical applications. Conventional wisdom suggests that not eve…