vix.ing · top · new · best · stats · spec

Shenyi Zhang

  1. JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
    2025/02/11 by Shenyi Zhang, Zhang, Shenyi, Keyan Guo +16 · 16 citations
    Computer Science · Psychology · #Digital and Cyber Forensics #Hate Speech and Cyberbullying Detection #Deception detection and forensic psychology
  2. Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
    2024/06/27 by Fang Zheng, Fang, Zheng, Tao Wang +15 · 3 citations
    Computer Science · #Adversarial Robustness in Machine Learning