Zhe Ye

4 papers · 2018–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze

Venues

AAAI (1) COLING (1) EMNLP (1) Interspeech (1)

Top co-authors

Diqun Yan (2) Wenjie Zhang (1) Terui Mao (1) Li Dong (1) Fang Li (1) Chenguang Wang (1) Yuzhou Nie (1) Vincent Siu (1) Wenbo Guo (1) Tianneng Shi (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Core AI (3) Security & Privacy (2) Learning Types (2) Privacy (2) Deep Learning (1) Architectures (1) Core Methods (1)

Keywords

backdoor attack (2) neural network security (1) black-box optimization (1) sentiment analysis (1) voice conversion (1) speaker recognition (1) speech classification (1) adversarial attack (1) convolutional neural network (1) deep neural network (1) word embedding (1) llm agent (1) sentiment lexicon (1) speech rate (1) indirect prompt injection (1) poison-only attack (1) adversarial learning (1) speech manipulation (1)

Papers

AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents EMNLP 2025 Speed Master: Quick or Slow Play to Attack Speaker Recognition AAAI 2025 Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion Interspeech 2023 Encoding Sentiment Information into Word Vectors for Sentiment Analysis COLING 2018