Get started
Author

Bochuan Cao

Observed names: Bochuan, Cao, Cao, Bochuan
Observed institution: Pennsylvania State University
ORCID: 0009-0007-1973-8186
Observed ORCID: 0009-0007-1973-8186
OpenAlex ID: A5030879739
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
2024 · Bochuan Cao, Yuanpu Cao, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 47
PDF
Jailbreak Open-Sourced Large Language Models via Enforced Decoding
2024 · Hangfan Zhang, Zhimeng Guo, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 7
PDF
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
2025 · Tianrong Zhang, Bochuan Cao, et al. · Findings of the Association for Computational Linguistics: NAACL · 5
PDF
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
2024 · Yuanpu Cao, Bochuan Cao, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 5
PDF
Data Free Backdoor Attacks
2024 · Bochuan Cao, Jinyuan Jia, et al. · neural information processing systems · 5
PDF
JoPA: Explaining Large Language Model’s Generation via Joint Prompt Attribution
2025 · Yurui Chang, Bochuan Cao, et al. · Annual Meeting of the Association for Computational Linguistics (ACL) · 4
PDF
On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?
2023 · Zhang, Hangfan, Guo, Zhimeng, et al. · arXiv (Cornell University) · 4
PDF
Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models
2024 · Li, Changjiang, Pang, Ren, et al. · arXiv (Cornell University) · 1
PDF
On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept
2024 · Liu, Guangliang, Mao, Haitao, et al. · arXiv (Cornell University) · 1
PDF
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks
2023 · Li, Changjiang, Pang, Ren, et al. · arXiv (Cornell University) · 1
PDF
SkillGrad: Optimizing Agent Skills Like Gradient Descent
2026 · Wang, Hanyu, Lan, Yifan, et al. · arXiv (Cornell University)
PDF
On the Convergence of Moral Self-Correction in Large Language Models
2025 · Association for Computational Linguistics 2025, Cao, Bochuan, et al. · Underline Science Inc.
You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
2025 · Bochuan Cao, Changjiang Li, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS)
On the Convergence of Moral Self-Correction in Large Language Models
2025 · Liu, Guangliang, Mao, Haitao, et al. · arXiv (Cornell University)
PDF
Your Agent Can Defend Itself against Backdoor Attacks
2025 · Changjiang, Li, Jiacheng, Liang, et al. · arXiv (Cornell University)
PDF
Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
2025 · Yurui Chang, Bochuan Cao, et al.
PDF
On the Convergence of Moral Self-Correction in Large Language Models
2025 · Guangliang Liu, Haitao Mao, et al. · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL)
PDF
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
2024 · Zeng, Yaopei, Cao, Yuanpu, et al. · arXiv (Cornell University)
PDF
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
2023 · Cao, Yuanpu, Cao, Bochuan, et al. · arXiv (Cornell University)
PDF
Works count: 24
Citation count: 80
H-index: 5
I10-index: 1
Year
Topic
Type