Xiaowei Huang

10

Papers

38

Total Citations

Papers (10)

MathAttack: Attacking Large Language Models towards Math Solving Ability

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Towards Better Robustness Against Natural Corruptions in Document Tampering Localization

Training Verification-Friendly Neural Networks via Neuron Behavior Consistency

A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection

GNS: Solving Plane Geometry Problems by Neural-Symbolic Reasoning with Multi-Modal LLMs

Towards Fairness-Aware Adversarial Learning

SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model

Position: Building Guardrails for Large Language Models Requires Systematic Design

Adversarial Training for Probabilistic Robustness