Cong Wang

RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models

SecMCP: Quantifying Conversation Drift in MCP via Latent Polytope

Refining Specs For LLM-Based RTL Agile Design

RL$^2$eak: Reinforcement Learning Enhanced Prompt Leakage Attack in Multi-tenant Large Language Model Services

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF

How Data Influence Changes in Training? Time-Varying Influence Measurement

Black-Box Guardrail Reverse-engineering Attack

Enhancing Query-Free Jailbreaks on Text-to-Image Models with Bimodal Guidance

Prediction Inconsistency Helps Generalizable Detection of Adversarial Examples

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture