Bochuan Cao

According to our database, Bochuan Cao authored at least 23 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

SkillGrad: Optimizing Agent Skills Like Gradient Descent.

Hanyu Wang, Yifan Lan, Bochuan Cao, Lu Lin, Jinghui Chen

CoRR, May, 2026

2025

Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models.

Chenxi Liu, Junjie Liang, Yuqi Jia, Bochuan Cao, Yang Bai, Heng Huang, Xun Chen

CoRR, November, 2025

Your Agent Can Defend Itself against Backdoor Attacks.

Changjiang Li, Jiacheng Liang, Bochuan Cao, Jinghui Chen, Ting Wang

CoRR, June, 2025

Watch the Watchers! On the Security Risks of Robustness-Enhancing Diffusion Models.

Changjiang Li, Ren Pang, Bochuan Cao, Jinghui Chen, Fenglong Ma, Shouling Ji, Ting Wang

Proceedings of the 34th USENIX Security Symposium, 2025

WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response.

Tianrong Zhang, Bochuan Cao, Yuanpu Cao, Lu Lin, Prasenjit Mitra, Jinghui Chen

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

On the Convergence of Moral Self-Correction in Large Language Models.

Guangliang Liu, Haitao Mao, Bochuan Cao, Xitong Zhang, Zhiyu Xue, Rongrong Wang, Kristen Marie Johnson

Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2025

AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models.

Yaopei Zeng, Yuanpu Cao, Bochuan Cao, Yurui Chang, Jinghui Chen, Lu Lin

Proceedings of the Forty-second International Conference on Machine Learning, 2025

TruthFlow: Truthful LLM Generation via Representation Flow Correction.

Hanyu Wang, Bochuan Cao, Yuanpu Cao, Jinghui Chen

Proceedings of the Forty-second International Conference on Machine Learning, 2025

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors.

Bochuan Cao, Changjiang Li, Yuanpu Cao, Yameng Ge, Ting Wang, Jinghui Chen

Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security, 2025

JoPA: Explaining Large Language Model's Generation via Joint Prompt Attribution.

Yurui Chang, Bochuan Cao, Yujia Wang, Jinghui Chen, Lu Lin

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation.

Yurui Chang, Bochuan Cao, Lu Lin

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models.

Changjiang Li, Ren Pang, Bochuan Cao, Jinghui Chen, Fenglong Ma, Shouling Ji, Ting Wang

CoRR, 2024

On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept.

Guangliang Liu, Haitao Mao, Bochuan Cao, Zhiyu Xue, Kristen Marie Johnson, Jiliang Tang, Rongrong Wang

CoRR, 2024

XPrompt:Explaining Large Language Model's Generation via Joint Prompt Attribution.

Yurui Chang, Bochuan Cao, Yujia Wang, Jinghui Chen, Lu Lin

CoRR, 2024

On the Difficulty of Defending Contrastive Learning against Backdoor Attacks.

Changjiang Li, Ren Pang, Bochuan Cao, Zhaohan Xi, Jinghui Chen, Shouling Ji, Ting Wang

Proceedings of the 33rd USENIX Security Symposium, 2024

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization.

Yuanpu Cao, Tianrong Zhang, Bochuan Cao, Ziyi Yin, Lu Lin, Fenglong Ma, Jinghui Chen

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Data Free Backdoor Attacks.

Bochuan Cao, Jinyuan Jia, Chuxuan Hu, Wenbo Guo, Zhen Xiang, Jinghui Chen, Bo Li, Dawn Song

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections.

Yuanpu Cao, Bochuan Cao, Jinghui Chen

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024

Jailbreak Open-Sourced Large Language Models via Enforced Decoding.

Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu, Bochuan Cao, Lu Lin, Jinyuan Jia, Jinghui Chen, Dinghao Wu

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM.

Bochuan Cao, Yuanpu Cao, Lu Lin, Jinghui Chen

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023

On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?

Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu, Bochuan Cao, Lu Lin, Jinyuan Jia, Jinghui Chen, Dinghao Wu

CoRR, 2023

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI.

Bochuan Cao, Changjiang Li, Ting Wang, Jinyuan Jia, Bo Li, Jinghui Chen

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time.

Huaxiu Yao, Caroline Choi, Bochuan Cao, Yoonho Lee, Pang Wei Koh, Chelsea Finn

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022