Bochuan Cao
~Bochuan_Cao1
12
论文总数
6.0
年均投稿
平均评分
接收情况4/12
会议分布
ICLR
8
NeurIPS
2
ICML
2
发表论文 (12 篇)
20256 篇
4
JoPA: Explaining Large Language Model's Generation via Joint Prompt Attribution
ICLR 2025withdrawn
5
TruthFlow: Truthful LLM Generation via Representation Flow Correction
ICML 2025Poster
3
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models
ICML 2025Poster
4
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
ICLR 2025Rejected
4
Your Agent Can Defend Itself against Backdoor Attacks
ICLR 2025withdrawn
5
Convergence Towards Stable Intrinsic Self-correction of Large Language Models
ICLR 2025Rejected
20246 篇
5
Data Free Backdoor Attacks
NeurIPS 2024Poster
3
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
ICLR 2024Rejected
4
Backdoor Attack for Federated Learning with Fake Clients
ICLR 2024withdrawn
3
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
NeurIPS 2024Poster
4
A Change of Heart: Backdoor Attacks on Security-Centric Diffusion Models
ICLR 2024Rejected
4
On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?
ICLR 2024withdrawn