Jiazhao Li

5 papers · 2020–2025 · 5 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 · Silver 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer

Venues

ACL (1) EMNLP (1) ICLR (1) NAACL (1) NeurIPS (1)

Top co-authors

Chaowei Xiao (4) Jiongxiao Wang (2) Bo Li (2) V.G. Vinod Vydiswaran (2) Zhuofeng Wu (2) Muhao Chen (2) Yixuan Li (1) SIYUAN MA (1) Yuting Ding (1) Xiujun Li (1)

Research topics

Artificial Intelligence (4) Machine Learning (4) Core AI (4) Application Areas (3) Learning Types · Machine Learning (3) Deep Learning (1) Natural Language Processing (1) Applications (1) Learning Types · Deep Learning (1)

Keywords

text classification (2) backdoor attack (2) machine unlearning (1) model interpretability (1) safety alignment (1) adversarial attack (1) generative model (1) adversarial defense (1) language model (1) poisoning attack (1) vision-language model (1) privacy protection (1) fine-tuning attack (1) membership inference (1) jailbreak defense (1) attribution method (1) text-to-text generation (1) large language model (1) facial identity (1) medical text simplification (1)

Papers

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset ICLR 2025 BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NeurIPS 2024 ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger NAACL 2024 Defending against Insertion-based Textual Backdoor Attacks via Attribution ACL 2023 PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions EMNLP 2020