学者档案2023-2025
Bochuan Cao
Pennsylvania State University
9论文数
0末位作者
11合作者人数
3一作
0独著
一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。
近期论文9
- JoPA: Explaining Large Language Model's Generation via Joint Prompt Attribution第 2 位,共 5 位作者ACL 2025
- Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation第 2 位,共 3 位作者ACL Findings 2025
- Watch the Watchers! On the Security Risks of Robustness-Enhancing Diffusion Models第 3 位,共 7 位作者USENIX Security 2025
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization第 3 位,共 7 位作者NeurIPS 2024 · 135 次引用
- Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM第 1 位,共 4 位作者ACL 2024 · 34 次引用
- Data Free Backdoor Attacks第 1 位,共 8 位作者NeurIPS 2024 · 12 次引用
- On the Difficulty of Defending Contrastive Learning against Backdoor Attacks第 3 位,共 7 位作者USENIX Security 2024 · 10 次引用
- Jailbreak Open-Sourced Large Language Models via Enforced Decoding第 4 位,共 8 位作者ACL 2024
- IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI第 1 位,共 6 位作者NeurIPS 2023 · 46 次引用
