PPaperPicks

Xixiang Lyu

2 papers at tracked venues · 2 at CORE A* · active 2024–2025

DBLP profile ↗ORCID search ↗

Venues

AAAI ×1ACM MM ×1

Frequent coauthors

Jing Ma
×2
Peihai Jiang
×1
Yige Li
×1
Haosen Sun
×1
Yiming Li
×1

Papers

  1. Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
    AAAI 2025 ·
    Peihai Jiang
    , Xixiang Lyu,
    Yige Li
    ,
    Jing Ma
  2. Learning from Distinction: Mitigating Backdoors Using a Low-Capacity Model
    ACM MM 2024 ·
    Haosen Sun
    ,
    Yiming Li
    , Xixiang Lyu,
    Jing Ma