PPaperPicks

Ke Xu

14 papers at tracked venues · 10 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

EMNLP ×4ACL ×2SIGKDD ×2AAAI ×1ACM MM ×1ICCV ×1ICLR ×1NeurIPS ×1WWW ×1

Frequent coauthors

Jianshuo Dong
DBLP profile ↗ORCID search ↗
×2
Qingjie Zhang
DBLP profile ↗ORCID search ↗
×2
Hongyao Yu
DBLP profile ↗ORCID search ↗
×1
Xiyuan Zhao
DBLP profile ↗ORCID search ↗
×1
Kuofeng Gao
DBLP profile ↗ORCID search ↗
×1
Yanling Wang
DBLP profile ↗ORCID search ↗
×1
Mingwei Zhan
DBLP profile ↗ORCID search ↗
×1
Hao Fang
DBLP profile ↗ORCID search ↗
×1
Li Gao
DBLP profile ↗ORCID search ↗
×1
Jiazhi Guan
DBLP profile ↗ORCID search ↗
×1
Bo Wu
DBLP profile ↗ORCID search ↗
×1
Rongwu Xu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering
    SIGKDD 2026 ·
    Hongyao Yu
    DBLP profile ↗ORCID search ↗
  2. Robust LLM-Based Website Fingerprinting under Dynamic Real-World Conditions
    WWW 2026 ·
    Xiyuan Zhao
    DBLP profile ↗ORCID search ↗
  3. "I've Decided to Leak": Probing Internals Behind Prompt Leakage Intents
    EMNLP 2025 ·
    Jianshuo Dong
    DBLP profile ↗ORCID search ↗
  4. An Engorgio Prompt Makes Large Language Model Babble on
    ICLR 2025 ·
    Jianshuo Dong
    DBLP profile ↗ORCID search ↗
  5. Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models
    ACL 2025 ·
    Kuofeng Gao
    DBLP profile ↗ORCID search ↗
  6. FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models
    EMNLP 2025 ·
    Yanling Wang
    DBLP profile ↗ORCID search ↗
  7. FlowRefiner: A Robust Traffic Classification Framework against Label Noise
    NeurIPS 2025 ·
    Mingwei Zhan
    DBLP profile ↗ORCID search ↗
  8. One Perturbation is Enough: On Generating Universal Adversarial Perturbations Against Vision-Language Pre-Training Models
    ICCV 2025 ·
    Hao Fang
    DBLP profile ↗ORCID search ↗
  9. Speculating LLMs' Chinese Training Data Pollution from Their Tokens
    EMNLP 2025 ·
    Qingjie Zhang
    DBLP profile ↗ORCID search ↗
  10. Understanding the Dark Side of LLMs' Intrinsic Self-Correction
    ACL 2025 ·
    Qingjie Zhang
    DBLP profile ↗ORCID search ↗
  11. Wedjat: Detecting Sophisticated Evasion Attacks via Real-time Causal Analysis
    SIGKDD 2025 ·
    Li Gao
    DBLP profile ↗ORCID search ↗
  12. Adversarial Robust Safeguard for Evading Deep Facial Manipulation
    AAAI 2024 ·
    Jiazhi Guan
    DBLP profile ↗ORCID search ↗
  13. Toward Timeliness-Enhanced Loss Recovery for Large-Scale Live Streaming
    ACM MM 2024 ·
    Bo Wu
    DBLP profile ↗ORCID search ↗
  14. Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
    EMNLP 2024 ·
    Rongwu Xu
    DBLP profile ↗ORCID search ↗