Kaiyuan Zhang

46 papers A* 19Journal 25Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Membership Inference Attacks Against Fine-tuned Diffusion Language Models.
CoRR
Yuetian Chen, Kaiyuan Zhang, Yuntao Du, Edoardo Stoppa, Charles Fleming, Ashish Kundu, Bruno Ribeiro, Ninghui Li
2026 J jnl
Security Considerations for Artificial Intelligence Agents.
CoRR
Ninghui Li, Kaiyuan Zhang, Kyle Polley, Jerry Ma
2026 J jnl
Window-based Membership Inference Attacks Against Fine-tuned Large Language Models.
CoRR
Yuetian Chen, Yuntao Du, Kaiyuan Zhang, Ashish Kundu, Charles Fleming, Bruno Ribeiro, Ninghui Li
2025 A* conf
BAIT: Large Language Model Backdoor Scanning by Inverting Attack Target.
SP
Guangyu Shen, Siyuan Cheng, Zhuo Zhang, Guanhong Tao, Kaiyuan Zhang, Hanxi Guo, Lu Yan, Xiaolong Jin, Shengwei An, Shiqing Ma, Xiangyu Zhang
2025 J jnl
BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents.
CoRR
Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley, Jerry Ma, Denis Yarats, Ninghui Li
2025 A* conf
CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling.
NDSS
Kaiyuan Zhang, Siyuan Cheng, Guangyu Shen, Bruno Ribeiro, Shengwei An, Pin-Yu Chen, Xiangyu Zhang, Ninghui Li
2025 J jnl
CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling.
CoRR
Kaiyuan Zhang, Siyuan Cheng, Guangyu Shen, Bruno Ribeiro, Shengwei An, Pin-Yu Chen, Xiangyu Zhang, Ninghui Li
2025 J jnl
Cascading and Proxy Membership Inference Attacks.
CoRR
Yuntao Du, Jiacheng Li, Yuetian Chen, Kaiyuan Zhang, Zhizhen Yuan, Hanshen Xiao, Bruno Ribeiro, Ninghui Li
2025 J jnl
CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs.
CoRR
Hanxi Guo, Siyuan Cheng, Kaiyuan Zhang, Guangyu Shen, Xiangyu Zhang
2025 J jnl
IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents.
CoRR
Shiwei Feng, Xiangzhe Xu, Xuan Chen, Kaiyuan Zhang, Syed Yusuf Ahmed, Zian Su, Mingwei Zheng, Xiangyu Zhang
2025 J jnl
LLM Agents Should Employ Security Principles.
CoRR
Kaiyuan Zhang, Zian Su, Pin-Yu Chen, Elisa Bertino, Xiangyu Zhang, Ninghui Li
2025 A* conf
ProSec: Fortifying Code LLMs with Proactive Security Alignment.
ICML
Xiangzhe Xu, Zian Su, Jinyao Guo, Kaiyuan Zhang, Zhenting Wang, Xiangyu Zhang
2025 A* conf
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis.
EMNLP
Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Guangyu Shen, Kaiyuan Zhang, Shengwei An, Guanhong Tao, Xiangyu Zhang
2025 A* conf
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks.
USENIX Security Symposium
Kaiyuan Zhang, Siyuan Cheng, Hanxi Guo, Yuetian Chen, Zian Su, Shengwei An, Yuntao Du, Charles Fleming, Ashish Kundu, Xiangyu Zhang, Ninghui Li
2025 J jnl
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks.
CoRR
Kaiyuan Zhang, Siyuan Cheng, Hanxi Guo, Yuetian Chen, Zian Su, Shengwei An, Yuntao Du, Charles Fleming, Ashish Kundu, Xiangyu Zhang, Ninghui Li
2025 — conf
System Prompt Hijacking via Permutation Triggers in LLM Supply Chains.
ACL (Findings)
Lu Yan, Siyuan Cheng, Xuan Chen, Kaiyuan Zhang, Guangyu Shen, Xiangyu Zhang
2025 J jnl
μKE: Matryoshka Unstructured Knowledge Editing of Large Language Models.
CoRR
Zian Su, Ziyang Huang, Kaiyuan Zhang, Xiangyu Zhang
2024 J jnl
ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs.
CoRR
Lu Yan, Siyuan Cheng, Xuan Chen, Kaiyuan Zhang, Guangyu Shen, Zhuo Zhang, Xiangyu Zhang
2024 A* conf
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens.
NeurIPS
Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Kaiyuan Zhang, Guanhong Tao, Guangyu Shen, Xiangyu Zhang
2024 A* conf
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift.
AAAI
Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang, Qiuling Xu, Guanhong Tao, Guangyu Shen, Siyuan Cheng, Shiqing Ma, Pin-Yu Chen, Tsung-Yi Ho, Xiangyu Zhang
2024 A* conf
Exploring the Orthogonality and Linearity of Backdoor Attacks.
SP
Kaiyuan Zhang, Siyuan Cheng, Guangyu Shen, Guanhong Tao, Shengwei An, Anuran Makur, Shiqing Ma, Xiangyu Zhang
2024 J jnl
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning.
CoRR
Siyuan Cheng, Guanhong Tao, Yingqi Liu, Guangyu Shen, Shengwei An, Shiwei Feng, Xiangzhe Xu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
2024 A* conf
Lotus: Evasive and Resilient Backdoor Attacks through Sub-Partitioning.
CVPR
Siyuan Cheng, Guanhong Tao, Yingqi Liu, Guangyu Shen, Shengwei An, Shiwei Feng, Xiangzhe Xu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
2024 A* conf
OdScan: Backdoor Scanning for Object Detection Models.
SP
Siyuan Cheng, Guangyu Shen, Guanhong Tao, Kaiyuan Zhang, Zhuo Zhang, Shengwei An, Xiangzhe Xu, Yingqi Li, Shiqing Ma, Xiangyu Zhang
2024 J jnl
ProSec: Fortifying Code LLMs with Proactive Security Alignment.
CoRR
Xiangzhe Xu, Zian Su, Jinyao Guo, Kaiyuan Zhang, Zhenting Wang, Xiangyu Zhang
2024 J jnl
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia.
CoRR
Guangyu Shen, Siyuan Cheng, Kaiyuan Zhang, Guanhong Tao, Shengwei An, Lu Yan, Zhuo Zhang, Shiqing Ma, Xiangyu Zhang
2024 A* conf
Rethinking the Invisible Protection against Unauthorized Image Usage in Stable Diffusion.
USENIX Security Symposium
Shengwei An, Lu Yan, Siyuan Cheng, Guangyu Shen, Kaiyuan Zhang, Qiuling Xu, Guanhong Tao, Xiangyu Zhang
2024 A* conf
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases.
NeurIPS
Zian Su, Xiangzhe Xu, Ziyang Huang, Kaiyuan Zhang, Xiangyu Zhang
2024 J jnl
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases.
CoRR
Zian Su, Xiangzhe Xu, Ziyang Huang, Kaiyuan Zhang, Xiangyu Zhang
2024 — conf
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening.
ECCV (62)
Siyuan Cheng, Guangyu Shen, Kaiyuan Zhang, Guanhong Tao, Shengwei An, Hanxi Guo, Shiqing Ma, Xiangyu Zhang
2024 J jnl
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening.
CoRR
Siyuan Cheng, Guangyu Shen, Kaiyuan Zhang, Guanhong Tao, Shengwei An, Hanxi Guo, Shiqing Ma, Xiangyu Zhang
2023 A* conf
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense.
NDSS
Siyuan Cheng, Guanhong Tao, Yingqi Liu, Shengwei An, Xiangzhe Xu, Shiwei Feng, Guangyu Shen, Kaiyuan Zhang, Qiuling Xu, Shiqing Ma, Xiangyu Zhang
2023 J jnl
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense.
CoRR
Siyuan Cheng, Guanhong Tao, Yingqi Liu, Shengwei An, Xiangzhe Xu, Shiwei Feng, Guangyu Shen, Kaiyuan Zhang, Qiuling Xu, Shiqing Ma, Xiangyu Zhang
2023 A* conf
Detecting Backdoors in Pre-trained Encoders.
CVPR
Shiwei Feng, Guanhong Tao, Siyuan Cheng, Guangyu Shen, Xiangzhe Xu, Yingqi Liu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
2023 J jnl
Detecting Backdoors in Pre-trained Encoders.
CoRR
Shiwei Feng, Guanhong Tao, Siyuan Cheng, Guangyu Shen, Xiangzhe Xu, Yingqi Liu, Kaiyuan Zhang, Shiqing Ma, Xiangyu Zhang
2023 A* conf
Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration.
NeurIPS
Guangyu Shen, Siyuan Cheng, Guanhong Tao, Kaiyuan Zhang, Yingqi Liu, Shengwei An, Shiqing Ma, Xiangyu Zhang
2023 J jnl
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift.
CoRR
Shengwei An, Sheng-Yen Chou, Kaiyuan Zhang, Qiuling Xu, Guanhong Tao, Guangyu Shen, Siyuan Cheng, Shiqing Ma, Pin-Yu Chen, Tsung-Yi Ho, Xiangyu Zhang
2023 A* conf
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning.
ICLR
Kaiyuan Zhang, Guanhong Tao, Qiuling Xu, Siyuan Cheng, Shengwei An, Yingqi Liu, Shiwei Feng, Guangyu Shen, Pin-Yu Chen, Shiqing Ma, Xiangyu Zhang
2023 A* conf
ImU: Physical Impersonating Attack for Face Recognition System with Natural Style Changes.
SP
Shengwei An, Yuan Yao, Qiuling Xu, Shiqing Ma, Guanhong Tao, Siyuan Cheng, Kaiyuan Zhang, Yingqi Liu, Guangyu Shen, Ian Kelk, Xiangyu Zhang
2023 A* conf
ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP.
NeurIPS
Lu Yan, Zhuo Zhang, Guanhong Tao, Kaiyuan Zhang, Xuan Chen, Guangyu Shen, Xiangyu Zhang
2023 J jnl
ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP.
CoRR
Lu Yan, Zhuo Zhang, Guanhong Tao, Kaiyuan Zhang, Xuan Chen, Guangyu Shen, Xiangyu Zhang
2023 A* conf
Your Exploit is Mine: Instantly Synthesizing Counterattack Smart Contract.
USENIX Security Symposium
Zhuo Zhang, Zhiqiang Lin, Marcelo Morales, Xiangyu Zhang, Kaiyuan Zhang
2022 J jnl
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning.
CoRR
Kaiyuan Zhang, Guanhong Tao, Qiuling Xu, Siyuan Cheng, Shengwei An, Yingqi Liu, Shiwei Feng, Guangyu Shen, Pin-Yu Chen, Shiqing Ma, Xiangyu Zhang
2021 J jnl
DRGraph: An Efficient Graph Layout Algorithm for Large-scale Graphs by Dimensionality Reduction.
IEEE Trans. Vis. Comput. Graph.
Minfeng Zhu, Wei Chen, Yuanzhe Hu, Yuxuan Hou, Liangjun Liu, Kaiyuan Zhang
2020 J jnl
DRGraph: An Efficient Graph Layout Algorithm for Large-scale Graphs by Dimensionality Reduction.
CoRR
Minfeng Zhu, Wei Chen, Yuanzhe Hu, Yuxuan Hou, Liangjun Liu, Kaiyuan Zhang
2019 J jnl
Enhancing statistical charts: toward better data visualization and analysis.
J. Vis.
Xiaonan Luo, Yuan Yuan, Kaiyuan Zhang, Jiazhi Xia, Zhiguang Zhou, Liang Chang, Tianlong Gu