Cheng Zhang

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.

The paper introduces Owner-Harm, a formal threat model addressing the critical blind spot of AI agents harming their own deployers, demonstrating that specialized defenses are needed beyond generic safety measures.

The paper introduces BadStyle, a novel backdoor attack framework that generates natural, stealthy poisoned samples using LLMs to compromise various LLMs with high success rates and robust activation.

This paper identifies a critical privacy vulnerability, termed Quantamination, where dynamic quantization in popular ML frameworks can leak sensitive user data across batch boundaries.

The paper introduces FinBoardBench, a novel evaluation suite using financial board games to demonstrate that current LLMs, despite strong static reasoning, fail at complex, dynamic wealth management and strategic decision-making.

This paper proposes two horizon-control strategies, Progressive OPD (POPD) and Truncated OPD (TOPD), demonstrating that full rollouts are often unnecessary for On-Policy Distillation, leading to significant improvements in training efficiency.

The paper proposes a sequence-alignment framework using Soft Dynamic Time Warping to evaluate audio-driven talking-head generation, demonstrating that this approach provides more robust and fair comparisons than traditional frame-wise metrics.