Get started
Author

Rui Ha

Observed name: Ha, Rui
OpenAlex ID: A5114601765
Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
2026 · Rui Pu, Chaozhuo Li, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1
PDF
Feint and Attack: Jailbreaking and Protecting LLMs via Attention Distribution Modeling
2025 · Rui Pu, Chaozhuo Li, et al. · International Joint Conference on Artificial Intelligence · 1
PDF
DSG-MCTS: A Dynamic Strategy-Guided Monte Carlo Tree Search for Diversified Reasoning in Large Language Models
2025 · Rui Ha, Chaozhuo Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1
PDF
BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting
2024 · Rui Pu, Chaozhuo Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1
PDF
MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting
2026 · Rui Pu, Chaozhuo Li, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
PDF
From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in LRMs via Decoupled Reasoning and Control
2026 · Rui Ha, Rui Pu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
MirrorShield: Towards Universal Defense Against Jailbreaks via Entropy-Guided Mirror Crafting
2025 · Pu, Rui, Li, Chaozhuo, et al. · arXiv (Cornell University)
PDF
Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
2024 · Pu, Rui, Li, Chaozhuo, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count: 4
H-index: 1
I10-index:
Year
Topic
Type