Profiles2023-2025
Bochuan Cao
Pennsylvania State University
9Papers
0Last author
11Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers9
- JoPA: Explaining Large Language Model's Generation via Joint Prompt AttributionAuthor 2 of 5ACL 2025
- Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during GenerationAuthor 2 of 3ACL Findings 2025
- Watch the Watchers! On the Security Risks of Robustness-Enhancing Diffusion ModelsAuthor 3 of 7USENIX Security 2025
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference OptimizationAuthor 3 of 7NeurIPS 2024 · 135 citations
- Defending Against Alignment-Breaking Attacks via Robustly Aligned LLMAuthor 1 of 4ACL 2024 · 34 citations
- Data Free Backdoor AttacksAuthor 1 of 8NeurIPS 2024 · 12 citations
- On the Difficulty of Defending Contrastive Learning against Backdoor AttacksAuthor 3 of 7USENIX Security 2024 · 10 citations
- Jailbreak Open-Sourced Large Language Models via Enforced DecodingAuthor 4 of 8ACL 2024
- IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AIAuthor 1 of 6NeurIPS 2023 · 46 citations
