6 papers
SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vision-Language Model Systems
Chung-En Johnny Yu, Brian Jalaian, Nathaniel D. Bastian
Combining multiple Vision-Language Models (VLMs) can enhance multimodal reasoning and robustness, but aggregating heterogeneous models' outputs amplifies uncertainty and increases…
Advancing Model Refinement: Muon-Optimized Distillation and Quantization for LLM Deployment
Jacob Sander, Brian Jalaian, Venkat R. Dasari
Large Language Models (LLMs) enable advanced natural language processing but face deployment challenges on resource-constrained edge devices due to high computational, memory, and…
Neurosymbolic AI Transfer Learning Improves Network Intrusion Detection
Huynh T. T. Tran, Jacob Sander, Achraf Cohen +2
Transfer learning is commonly utilized in various fields such as computer vision, natural language processing, and medical imaging due to its impressive capability to address subta…
Towards Interpretable Adversarial Examples via Sparse Adversarial Attack
Fudong Lin, Jiadong Lou, Hao Wang +2
Sparse attacks are to optimize the magnitude of adversarial perturbations for fooling deep neural networks (DNNs) involving only a few perturbed pixels (i.e., under the l0 constrai…
Neurosymbolic Artificial Intelligence for Robust Network Intrusion Detection: From Scratch to Transfer Learning
Huynh T. T. Tran, Jacob Sander, Achraf Cohen +2
Network Intrusion Detection Systems (NIDS) play a vital role in protecting digital infrastructures against increasingly sophisticated cyber threats. In this paper, we extend ODXU,…
Hydra: An Agentic Reasoning Approach for Enhancing Adversarial Robustness and Mitigating Hallucinations in Vision-Language Models
Chung-En, Yu, Hsuan-Chih +3
To develop trustworthy Vision-Language Models (VLMs), it is essential to address adversarial robustness and hallucination mitigation, both of which impact factual accuracy in high-…