Xiangyu Yin

19 papers A* 4Journal 13Unranked 2
YearRankTypeTitle / Venue / Authors
2026 A* conf
Fragile by Design: On the Limits of Adversarial Defenses in Personalized DreamBooth Generation.
AAAI
Zhen Chen, Yi Zhang, Xiangyu Yin, Chengxuan Qin, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
2025 A* conf
A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection.
AAAI
Fu Wang, Yanghao Zhang, Xiangyu Yin, Guangliang Cheng, Zeyu Fu, Xiaowei Huang, Wenjie Ruan
2025 J jnl
CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models.
CoRR
Xiangyu Yin, Jiaxu Liu, Zhen Chen, Jinwei Hu, Yi Dong, Xiaowei Huang, Wenjie Ruan
2025 J jnl
FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model.
CoRR
Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan, Guangliang Cheng, Yi Dong, Xiaowei Huang
2025 J jnl
Fragile by Design: On the Limits of Adversarial Defenses in Personalized Generation.
CoRR
Zhen Chen, Yi Zhang, Xiangyu Yin, Chengxuan Qin, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
2025 — conf
Interpreting Safety: A LLM and STPA Approach.
PRICAI (4)
Yi Qi, Shufeng Chen, Xiangyu Yin, Wenjie Ruan, Siddartha Khastgir, Ji Ruan, Xingyu Zhao, Xiaowei Huang
2025 J jnl
TAIJI: Textual Anchoring for Immunizing Jailbreak Images in Vision Language Models.
CoRR
Xiangyu Yin, Yi Qi, Jinwei Hu, Zhen Chen, Yi Dong, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
2025 J jnl
Toward Linearly Regularizing the Geometric Bottleneck of Linear Generalized Attention.
Trans. Mach. Learn. Res.
Jiaxu Liu, Xinping Yi, Xiangyu Yin, Yuhang Song, Gaojie Jin, Xiaowei Huang
2024 J jnl
A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detection.
CoRR
Fu Wang, Yanghao Zhang, Xiangyu Yin, Guangliang Cheng, Zeyu Fu, Xiaowei Huang, Wenjie Ruan
2024 A* conf
Boosting Adversarial Training via Fisher-Rao Norm-Based Regularization.
CVPR
Xiangyu Yin, Wenjie Ruan
2024 J jnl
Boosting Adversarial Training via Fisher-Rao Norm-based Regularization.
CoRR
Xiangyu Yin, Wenjie Ruan
2024 — conf
Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE.
ECML/PKDD (3)
Jiaxu Liu, Xinping Yi, Sihao Wu, Xiangyu Yin, Tianle Zhang, Xiaowei Huang, Shi Jin
2024 J jnl
Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE.
CoRR
Jiaxu Liu, Xinping Yi, Sihao Wu, Xiangyu Yin, Tianle Zhang, Xiaowei Huang, Shi Jin
2024 J jnl
DIMBA: discretely masked black-box attack in single object tracking.
Mach. Learn.
Xiangyu Yin, Wenjie Ruan, Jonathan E. Fieldsend
2024 A* conf
Representation-Based Robustness in Goal-Conditioned Reinforcement Learning.
AAAI
Xiangyu Yin, Sihao Wu, Jiaxu Liu, Meng Fang, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
2024 J jnl
Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving.
CoRR
Sihao Wu, Jiaxu Liu, Xiangyu Yin, Guangliang Cheng, Xingyu Zhao, Meng Fang, Xinping Yi, Xiaowei Huang
2024 J jnl
Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming.
CoRR
Jiaxu Liu, Xiangyu Yin, Sihao Wu, Jianhong Wang, Meng Fang, Xinping Yi, Xiaowei Huang
2023 J jnl
ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning.
CoRR
Xiangyu Yin, Sihao Wu, Jiaxu Liu, Meng Fang, Xingyu Zhao, Xiaowei Huang, Wenjie Ruan
2022 J jnl
DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking.
CoRR
Xiangyu Yin, Wenjie Ruan, Jonathan E. Fieldsend