Zhaohan Xi

5 papers · 2023–2025 · 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (14)

Venues

EMNLP (1) ICCV (1) ICLR (1) NAACL (1) NeurIPS (1)

Top co-authors

Ting Wang (4) Ren Pang (3) Changjiang Li (3) Shouling Ji (3) Jinghui Chen (2) Tianyu Du (2) Tianrong Zhang (1) Weicheng Ma (1) Yuan Yao (1) Luoxi Tang (1)

Research topics

Artificial Intelligence (5) Core AI (5) Machine Learning (4) Learning Types · Machine Learning (4) Deep Learning (2) Learning Types · Deep Learning (2) Natural Language Processing (1) Learning Paradigms (1) Resources & Methods (1)

Keywords

backdoor attack (3) few-shot learning (2) adversarial defense (2) self-supervised learning (1) neural architecture search (1) harmful content (1) safety alignment (1) model alignment (1) adversarial attack (1) pre-trained language model (1) attack transferability (1) trigger pattern (1) data curation (1) model customization (1) trigger inversion (1) large language model (1) representation invariance (1) harmful content mitigation (1) backdoor removal (1) adversarial prompt tuning (1)

Papers

Data to Defense: The Role of Curation in Aligning Large Language Models Against Safety Compromise EMNLP 2025 PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning NAACL 2024 An Embarrassingly Simple Backdoor Attack on Self-supervised Learning ICCV 2023 Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks NeurIPS 2023 The Dark Side of AutoML: Towards Architectural Backdoor Search ICLR 2023