Bao-di Liu

3 papers · 2024–2026 · 2 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

EMNLP (2) ACL (1)

Top co-authors

Xinghao Yang (3) Weifeng Liu (3) Wei Liu (2) Ao Wang (2) Yidan Xu (1) Yongshun Gong (1) Chen Li (1)

Research topics

Artificial Intelligence (3) Core AI (3) Deep Learning (2) Machine Learning (2) Learning Types · Machine Learning (2) Learning Types · Deep Learning (2) Optimization & Theory (2) Natural Language Processing (1) Application Areas (1) Applications (1) Core Methods (1)

Keywords

adversarial attack (2) text classification (2) feature disentanglement (1) natural gradient (1) mutual information (1) disentangled representation (1) adversarial defense (1) jailbreak attack (1) adversarial text (1) attack success rate (1) chinese text (1) robust feature (1) chinese text processing (1) cross-model transferability (1) text attack (1) immune algorithm (1) sound-shape code (1) text adversarial attack (1) adversarial text defense (1) reparameterization invariance (1)

Papers

Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance ACL 2026 Disentangled Information Bottleneck for Adversarial Text Defense EMNLP 2025 Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks EMNLP 2024