Heng Huang

This paper introduces a component-centric framework and a novel detector, Connor, to understand and detect sophisticated, multi-component attacks targeting the Model Context Protocol (MCP) servers.

This paper provides the first comprehensive systematization and large-scale empirical evaluation of existing LLM-based Automated Penetration Testing (AutoPT) frameworks, offering a structured taxonomy and unified benchmark for the field.

FedAttr introduces a novel client-level attribution protocol for Federated Learning (FL) that accurately identifies which clients trained on watermarked data while maintaining strong privacy guarantees.

The paper introduces a history-aware adaptive Reduced-Order Model (ROM) framework using incremental Singular Value Decomposition (iSVD) that maintains accuracy for online dynamics far beyond the initial training data regime.

DeepSurvey is an agentic system that significantly enhances automated survey generation by extracting deep, structured knowledge from full-text papers and rigorously validating citations, achieving superior content depth and reliability compared to existing methods.

The paper introduces Source-Grounded Semantic Reinforcement Learning (SG-SRL), a framework that leverages abundant source-language monolingual data to improve target-language generation in low-resource settings by providing cross-lingual semantic supervision.

This paper introduces Capability Self-Assessment (CSA), a crucial ability for LLMs to recognize their limitations, and demonstrates that reinforcement learning is an effective method for teaching this skill without degrading the model's core capabilities.