← Search

Yinghan Zhou

2 accepted papers

2026

BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation

AAAI 2026technical

Although existing backdoor defenses have gained success in mitigating backdoor attacks, they still face substantial challenges. In particular, most of them rely on large amounts of clean data to weaken the backdoor mapping but generally struggle with residual trigger effects, resulting in persistent

Cited by 0SourcePDFScholar
2025

Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations

NAACL 2025long

The growing popularity of large language models has raised concerns regarding the potential to misuse AI-generated text (AIGT). It becomes increasingly critical to establish an excellent AIGT detection method with high generalization and robustness.While, existing methods either focus on model gener…