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

Shanu Sushmita

  1. PADBen: A Comprehensive Benchmark for Evaluating AI Text Detectors Against Paraphrase Attacks
    2025/11/01 by Yiwei Zha, Rui Min, Zha, Yiwei +3 · 1 citation
    Computer Science · #Authorship Attribution and Profiling #Topic Modeling #Hate Speech and Cyberbullying Detection
  2. Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks
    2026/07/29 by Haoyu Zhang, Zhuoxi Wang, Shibo Zheng +4
    Computer Science · #cs.AI #cs.CR #cs.LG
  3. Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses
    2026/07/29 by Haoyu Zhang, Shibo Zheng, Xiangchen Guan +4
    Computer Science · #cs.AI #cs.CR
  4. Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks
    2026/08/02 by Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2
    Computer Science · #cs.AI #cs.CR