default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSiyuan Liang 0004
Person information
- affiliation: National University of Singapore, School of Computer of Science, Singapore
- affiliation (former): Chinese Academy of Sciences, Institute of Information Engineering, Beijing, China
Other persons with the same name
- Siyuan Liang — disambiguation page
- Siyuan Liang 0001
![[0000-0001-7865-1530]](https://dblp.org/img/orcid-mark.12x12.png "0000-0001-7865-1530")
— Taiyuan University of Technology, Shanxi, China - Siyuan Liang 0002 — Chinese University of Hong Kong, Hong Kong, SAR, China
- Siyuan Liang 0003 — Xi'an University of Posts and Telecommunications, China
- Siyuan Liang 0005 — China Electric Power Research Institute, Wuhan, China
Other persons with a similar name
SPARQL queries 
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
showing all ?? records
2020 – today
- 2026
[j18]Zheng Yi Ho, Siyuan Liang, Dacheng Tao:
Understanding Hallucinations in Large Visual and Language Models. ACM Comput. Surv. 58(13): 332:1-332:36 (2026)- [j17]Zonghao Ying, Aishan Liu, Siyuan Liang, Lei Huang, Jinyang Guo, Wenbo Zhou, Xianglong Liu, Dacheng Tao:
SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models. Int. J. Comput. Vis. 134(1): 18 (2026) - [j16]Siyuan Liang, Jiayang Liu, Jiecheng Zhai, Tianmeng Fang, Rongcheng Tu, Aishan Liu, Xiaochun Cao, Dacheng Tao:
T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models. Int. J. Comput. Vis. 134(4): 144 (2026) - [j15]Jiajun Gong, Wei Cai, Siyuan Liang, Zhong Guan, Tao Wang, Ee-Chien Chang:
WFCAT: Augmenting Website Fingerprinting With Channel-Wise Attention on Timing Features. IEEE Trans. Dependable Secur. Comput. 23(1): 149-163 (2026) - [j14]Zonglei Jing, Zonghao Ying, Le Wang, Siyuan Liang, Xiaoqian Li, Mingchuan Zhang, Aishan Liu, Xianglong Liu, Dacheng Tao:
CogMorph: Cognitive Morphing Attacks for Text-to-Image Models. IEEE Trans. Dependable Secur. Comput. 23(3): 5287-5301 (2026) - [j13]Siyuan Liang, Jiajun Gong, Tianmeng Fang, Aishan Liu, Tao Wang, Xiaochun Cao, Dacheng Tao, Ee-Chien Chang:
TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning. IEEE Trans. Inf. Forensics Secur. 21: 2610-2625 (2026) - [c42]Shuhan Xu, Siyuan Liang, Hongling Zheng, Aishan Liu, Xinbiao Wang, Yong Luo, Fu Lin, Leszek Rutkowski, Dacheng Tao:
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs. AAAI 2026: 11397-11405 - [c41]Jiangfan Liu, Yongkang Guo, Fangzhi Zhong, Tianyuan Zhang, Zonglei Jing, Siyuan Liang, Jiakai Wang, Mingchuan Zhang, Aishan Liu, Xianglong Liu:
Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles. AAAI 2026: 38926-38934 - [c40]Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao:
Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees. ACL (1) 2026: 30122-30143 - [i89]Zhiyao Ren, Yibing Zhan, Siyuan Liang, Guozheng Ma, Baosheng Yu, Dacheng Tao:
Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation. CoRR abs/2601.15645 (2026) - [i88]Siyuan Liang, Yongcheng Jing, Yingjie Wang, Jiaxing Huang, Ee-Chien Chang, Dacheng Tao:
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning. CoRR abs/2602.17168 (2026) - [i87]Zhixiang Guo, Siyuan Liang, Andras Balogh, Noah Lunberry, Rong-Cheng Tu, Márk Jelasity, Dacheng Tao:
When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models. CoRR abs/2602.18739 (2026) - [i86]Shuhan Xu, Siyuan Liang, Hongling Zheng, Yong Luo, Han Hu, Lefei Zhang, Dacheng Tao:
CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models. CoRR abs/2603.13435 (2026) - [i85]Tianrui Lou, Siyuan Liang, Jiawei Liang, Yuze Gao, Xiaochun Cao:
R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting. CoRR abs/2603.26067 (2026) - [i84]Sihan Ma, Siyuan Liang, Dacheng Tao:
Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models. CoRR abs/2605.18132 (2026) - [i83]Quang Duc Nguyen, Siyuan Liang, Yiming Li, Fushuo Huo, Dacheng Tao:
TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting. CoRR abs/2605.22365 (2026) - [i82]Zhixiang Guo, Siyuan Liang, Shi Fu, Cheng Guo, Andras Balogh, Márk Jelasity, Dacheng Tao:
WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents. CoRR abs/2605.23220 (2026) - [i81]Leyi Qi, Yiming Li, Siyuan Liang, Zhengzhong Tu, Dacheng Tao:
Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing. CoRR abs/2605.29809 (2026) - 2025
- [j12]Aishan Liu, Xianglong Liu, Xinwei Zhang, Yisong Xiao, Yuguang Zhou, Siyuan Liang, Jiakai Wang, Xiaochun Cao, Dacheng Tao:
Pre-trained Trojan Attacks for Visual Recognition. Int. J. Comput. Vis. 133(6): 3568-3585 (2025) - [j11]Jiawei Liang, Siyuan Liang, Aishan Liu, Xiaochun Cao:
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models. Int. J. Comput. Vis. 133(7): 3994-4013 (2025) - [j10]Yisong Xiao, Xianglong Liu, QianJia Cheng, Zhenfei Yin, Siyuan Liang, Jiapeng Li, Jing Shao, Aishan Liu, Dacheng Tao:
GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing. Int. J. Comput. Vis. 133(12): 8332-8355 (2025) - [j9]Jian Li, Yibo Fan, Ruoyu Chen, Siyuan Liang, Yifei Feng, Ying He, Yuliang Zhao:
An Intelligent Badminton Handle With Multinode MEMS Sensors for Explainable Motion Recognition. IEEE Internet Things J. 12(18): 37022-37034 (2025) - [j8]Yisong Xiao, Aishan Liu, Siyuan Liang, Xianglong Liu, Dacheng Tao:
Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models. Proc. ACM Softw. Eng. 2(ISSTA): 250-273 (2025) - [j7]Aishan Liu, Yuguang Zhou, Xianglong Liu, Tianyuan Zhang, Siyuan Liang, Jiakai Wang, Yanjun Pu, Tianlin Li, Junqi Zhang, Wenbo Zhou, Qing Guo, Dacheng Tao:
Compromising LLM Driven Embodied Agents With Contextual Backdoor Attacks. IEEE Trans. Inf. Forensics Secur. 20: 3979-3994 (2025) - [j6]Zonghao Ying, Aishan Liu, Tianyuan Zhang, Zhengmin Yu, Siyuan Liang, Xianglong Liu, Dacheng Tao:
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt. IEEE Trans. Inf. Forensics Secur. 20: 7153-7165 (2025) - [j5]Jiajun Gong, Guotao Meng, Wei Cai, Siyuan Liang, Tao Wang, Ee-Chien Chang:
FOADA: Toward Robust Open-World Mobile App Fingerprinting. IEEE Trans. Inf. Forensics Secur. 20: 8014-8029 (2025) - [j4]Muxue Liang, Chuan Wang, Siyuan Liang, Aishan Liu, Yanan Cao, Qingyong Li, Zeming Liu, Liang Yang, Xiaochun Cao:
Hard-Label Black-Box Adversarial Attacks for Implicit Scene Interactions. IEEE Trans. Inf. Forensics Secur. 20: 10346-10360 (2025) - [j3]Yuan Xun, Siyuan Liang, Xiaojun Jia, Xinwei Liu, Jun Chen, Xiaochun Cao:
CleanerCLIP: Fine-Grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning. IEEE Trans. Inf. Forensics Secur. 20: 12404-12416 (2025) - [c39]Xuxu Liu, Siyuan Liang, Mengya Han, Yong Luo, Aishan Liu, Xiantao Cai, Zheng He, Dacheng Tao:
ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models. ACL (1) 2025: 17928-17947 - [c38]Siyuan Liang, Jiawei Liang, Tianyu Pang, Chao Du, Aishan Liu, Mingli Zhu, Xiaochun Cao, Dacheng Tao:
Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift. CVPR 2025: 9477-9486 - [c37]Ruoyu Chen, Siyuan Liang, Jingzhi Li, Shiming Liu, Maosen Li, Zhen Huang, Hua Zhang, Xiaochun Cao:
Interpreting Object-level Foundation Models via Visual Precision Search. CVPR 2025: 30042-30052 - [c36]Zonghao Ying, Deyue Zhang, Zonglei Jing, Yisong Xiao, Quanchen Zou, Aishan Liu, Siyuan Liang, Xiangzheng Zhang, Xianglong Liu, Dacheng Tao:
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models. EMNLP (Findings) 2025: 17138-17157 - [c35]Jiawei Liang, Siyuan Liang, Tianrui Lou, Ming Zhang, Wenjin Li, Dunqiu Fan, Xiaochun Cao:
Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion. ICCV 2025: 13880-13889 - [c34]Zhixiang Guo, Siyuan Liang, Aishan Liu, Dacheng Tao:
CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks. ICCV 2025: 19417-19426 - [c33]Shuchao Pang, Zhenghan Chen, Shen Zhang, Liming Lu, Siyuan Liang, Anan Du, Yongbin Zhou:
Towards a 3D Transfer-Based Black-Box Attack via Critical Feature Guidance. ICCV 2025: 26912-26922 - [c32]Tianrui Lou, Xiaojun Jia, Siyuan Liang, Jiawei Liang, Ming Zhang, Yanjun Xiao, Xiaochun Cao:
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation. ICCV 2025: 28752-28762 - [c31]Zheng Yi Ho, Siyuan Liang, Sen Zhang, Yibing Zhan, Dacheng Tao:
NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models. ICLR 2025 - [c30]Zhiyao Ren, Siyuan Liang, Aishan Liu, Dacheng Tao:
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks. ICML 2025 - [c29]Yisong Xiao, Aishan Liu, Xinwei Zhang, Tianyuan Zhang, Tianlin Li, Siyuan Liang, Xianglong Liu, Yang Liu, Dacheng Tao:
BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks. ICSE 2025: 3123-3135 - [c28]Jiawei Liang, Siyuan Liang, Jianjie Huang, Chenxi Si, Ming Zhang, Xiaochun Cao:
Physical Adversarial Camouflage Through Gradient Calibration and Regularization. IJCAI 2025: 1521-1529 - [c27]Le Wang, Zonghao Ying, Tianyuan Zhang, Siyuan Liang, Shengshan Hu, Mingchuan Zhang, Aishan Liu, Xianglong Liu:
Manipulating Multimodal Agents via Cross-Modal Prompt Injection. ACM Multimedia 2025: 10955-10964 - [c26]Aishan Liu, Jiakai Wang, Tianyuan Zhang, Hainan Li, Jiangfan Liu, Siyuan Liang, Yilong Ren, Xianglong Liu, Dacheng Tao:
MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving. ACM Multimedia 2025: 13474-13476 - [c25]Xuan Wang, Siyuan Liang, Dongping Liao, Han Fang, Aishan Liu, Xiaochun Cao, Yu-liang Lu, Ee-Chien Chang, Xitong Gao:
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework. NeurIPS 2025 - [c24]Kuanrong Liu, Siyuan Liang, Cheng Qian, Ming Zhang, Xiaochun Cao:
Bridging the Task Gap: Multi-task Adversarial Transferability in CLIP and Its Derivatives. PRCV (4) 2025: 152-166 - [i80]Zonglei Jing, Zonghao Ying, Le Wang, Siyuan Liang, Aishan Liu, Xianglong Liu, Dacheng Tao:
CogMorph: Cognitive Morphing Attacks for Text-to-Image Models. CoRR abs/2501.11815 (2025) - [i79]Lu Wang, Tianyuan Zhang, Yang Qu, Siyuan Liang, Yuwei Chen, Aishan Liu, Xianglong Liu, Dacheng Tao:
Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving. CoRR abs/2501.13563 (2025) - [i78]Zonghao Ying, Deyue Zhang, Zonglei Jing, Yisong Xiao, Quanchen Zou, Aishan Liu, Siyuan Liang, Xiangzheng Zhang, Xianglong Liu, Dacheng Tao:
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models. CoRR abs/2502.11054 (2025) - [i77]Xuxu Liu, Siyuan Liang, Mengya Han, Yong Luo, Aishan Liu, Xiantao Cai, Zheng He, Dacheng Tao:
ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models. CoRR abs/2502.18511 (2025) - [i76]Liming Lu, Shuchao Pang, Siyuan Liang, Haotian Zhu, Xiyu Zeng, Aishan Liu, Yunhuai Liu, Yongbin Zhou:
Adversarial Training for Multimodal Large Language Models against Jailbreak Attacks. CoRR abs/2503.04833 (2025) - [i75]Xuan Wang, Siyuan Liang, Dongping Liao, Han Fang, Aishan Liu, Xiaochun Cao, Yu-liang Lu, Ee-Chien Chang, Xitong Gao:
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework. CoRR abs/2503.16872 (2025) - [i74]Ruoyu Chen, Siyuan Liang, Jingzhi Li, Shiming Liu, Li Liu, Hua Zhang, Xiaochun Cao:
Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection. CoRR abs/2504.00470 (2025) - [i73]Yisong Xiao, Aishan Liu, Siyuan Liang, Xianglong Liu, Dacheng Tao:
Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models. CoRR abs/2504.07787 (2025) - [i72]Le Wang, Zonghao Ying, Tianyuan Zhang, Siyuan Liang, Shengshan Hu, Mingchuan Zhang, Aishan Liu, Xianglong Liu:
Manipulating Multimodal Agents via Cross-Modal Prompt Injection. CoRR abs/2504.14348 (2025) - [i71]Siyuan Liang, Jiayang Liu, Jiecheng Zhai, Tianmeng Fang, Rongcheng Tu, Aishan Liu, Xiaochun Cao, Dacheng Tao:
T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models. CoRR abs/2504.15512 (2025) - [i70]Ming Liu, Siyuan Liang, Koushik Howlader, Liwen Wang, Dacheng Tao, Wensheng Zhang:
Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving. CoRR abs/2505.06413 (2025) - [i69]Jiayang Liu, Siyuan Liang, Shiqian Zhao, Rongcheng Tu, Wenbo Zhou, Xiaochun Cao, Dacheng Tao, Siew Kei Lam:
Jailbreaking the Text-to-Video Generative Models. CoRR abs/2505.06679 (2025) - [i68]Wenqiang Wang, Siyuan Liang, Yangshijie Zhang, Xiaojun Jia, Hao Lin, Xiaochun Cao:
No Query, No Access. CoRR abs/2505.07258 (2025) - [i67]Shuhan Xu, Siyuan Liang, Hongling Zheng, Yong Luo, Aishan Liu, Dacheng Tao:
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs. CoRR abs/2506.04743 (2025) - [i66]Yuan Xun, Siyuan Liang, Xiaojun Jia, Xinwei Liu, Xiaochun Cao:
Robust Anti-Backdoor Instruction Tuning in LVLMs. CoRR abs/2506.05401 (2025) - [i65]Zonghao Ying, Siyang Wu, Run Hao, Peng Ying, Shixuan Sun, Pengyu Chen, Junze Chen, Hao Du, Kaiwen Shen, Shangkun Wu, Jiwei Wei, Shiyuan He, Yang Yang, Xiaohai Xu, Ke Ma, Qianqian Xu, Qingming Huang, Shi Lin, Xun Wang, Changting Lin, Meng Han, Yilei Jiang, Siqi Lai, Yaozhi Zheng, Yifei Song, Xiangyu Yue, Zonglei Jing, Tianyuan Zhang, Zhilei Zhu, Aishan Liu, Jiakai Wang, Siyuan Liang, Xianglong Kong, Hainan Li, Junjie Mu, Haotong Qin, Yue Yu, Lei Chen, Felix Juefei-Xu, Qing Guo, Xinyun Chen, Yew Soon Ong, Xianglong Liu, Dawn Song, Alan L. Yuille, Philip Torr, Dacheng Tao:
Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025. CoRR abs/2506.12430 (2025) - [i64]Xuan Wang, Siyuan Liang, Zhe Liu, Yi Yu, Yuliang Lu, Xiaochun Cao, Ee-Chien Chang, Xitong Gao:
Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments. CoRR abs/2506.13205 (2025) - [i63]Aishan Liu, Zonghao Ying, Le Wang, Junjie Mu, Jinyang Guo, Jiakai Wang, Yuqing Ma, Siyuan Liang, Mingchuan Zhang, Xianglong Liu, Dacheng Tao:
AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions. CoRR abs/2506.14697 (2025) - [i62]Siyuan Liang, Tianmeng Fang, Zhe Liu, Aishan Liu, Yan Xiao, Jinyuan He, Ee-Chien Chang, Xiaochun Cao:
SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents. CoRR abs/2507.00841 (2025) - [i61]Zhiyao Ren, Siyuan Liang, Aishan Liu, Dacheng Tao:
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks. CoRR abs/2507.01321 (2025) - [i60]Tianrui Lou, Xiaojun Jia, Siyuan Liang, Jiawei Liang, Ming Zhang, Yanjun Xiao, Xiaochun Cao:
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation. CoRR abs/2507.01367 (2025) - [i59]Zonglei Jing, Xiao Yang, Xiaoqian Li, Siyuan Liang, Aishan Liu, Mingchuan Zhang, Xianglong Liu:
PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation. CoRR abs/2508.01272 (2025) - [i58]Tianyuan Zhang, Ting Jin, Lu Wang, Jiangfan Liu, Siyuan Liang, Mingchuan Zhang, Aishan Liu, Xianglong Liu:
Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving. CoRR abs/2508.02028 (2025) - [i57]Jiawei Liang, Siyuan Liang, Jianjie Huang, Chenxi Si, Ming Zhang, Xiaochun Cao:
Physical Adversarial Camouflage through Gradient Calibration and Regularization. CoRR abs/2508.05414 (2025) - [i56]Aishan Liu, Jiakai Wang, Tianyuan Zhang, Hainan Li, Jiangfan Liu, Siyuan Liang, Yilong Ren, Xianglong Liu, Dacheng Tao:
MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving. CoRR abs/2508.06534 (2025) - [i55]Shixuan Sun, Siyuan Liang, Ruoyu Chen, Jianjie Huang, Jingzhi Li, Xiaochun Cao:
SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling. CoRR abs/2508.09105 (2025) - [i54]Jiangfan Liu, Yongkang Guo, Fangzhi Zhong, Tianyuan Zhang, Zonglei Jing, Siyuan Liang, Jiakai Wang, Mingchuan Zhang, Aishan Liu, Xianglong Liu:
Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles. CoRR abs/2508.14527 (2025) - [i53]Shuchao Pang, Zhenghan Chen, Shen Zhang, Liming Lu, Siyuan Liang, Anan Du, Yongbin Zhou:
Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance. CoRR abs/2508.15650 (2025) - [i52]Dehong Kong, Sifan Yu, Siyuan Liang, Jiawei Liang, Jianhou Gan, Aishan Liu, Wenqi Ren:
Universal Camouflage Attack on Vision-Language Models for Autonomous Driving. CoRR abs/2509.20196 (2025) - [i51]Zhengxiao Li, Liming Lu, Xu Zheng, Siyuan Liang, Zhenghan Chen, Yongbin Zhou, Shuchao Pang:
FERD: Fairness-Enhanced Data-Free Robustness Distillation. CoRR abs/2509.20793 (2025) - [i50]Xiyu Zeng, Siyuan Liang, Liming Lu, Haotian Zhu, Enguang Liu, Jisheng Dang, Yongbin Zhou, Shuchao Pang:
SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision-Language Models. CoRR abs/2509.21400 (2025) - [i49]Enguang Liu, Siyuan Liang, Liming Lu, Xiyu Zeng, Xiaochun Cao, Aishan Liu, Shuchao Pang:
RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation. CoRR abs/2509.22356 (2025) - [i48]Wenqiang Wang, Siyuan Liang, Yan Xiao, Xiaochun Cao:
Text Adversarial Attacks with Dynamic Outputs. CoRR abs/2509.22393 (2025) - [i47]Jiawei Liang, Ruoyu Chen, Xianghao Jiao, Siyuan Liang, Shiming Liu, Qunli Zhang, Zheng Hu, Xiaochun Cao:
Explaining multimodal LLMs via intra-modal token interactions. CoRR abs/2509.22415 (2025) - [i46]Ruoyu Chen, Xiaoqing Guo, Kangwei Liu, Siyuan Liang, Shiming Liu, Qunli Zhang, Hua Zhang, Xiaochun Cao:
Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation. CoRR abs/2509.22496 (2025) - [i45]Kuanrong Liu, Siyuan Liang, Cheng Qian, Ming Zhang, Xiaochun Cao:
Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivatives. CoRR abs/2509.23917 (2025) - [i44]Zheng Yi Ho, Siyuan Liang, Dacheng Tao:
Review of Hallucination Understanding in Large Language and Vision Models. CoRR abs/2510.00034 (2025) - [i43]Yisong Xiao, Aishan Liu, Siyuan Liang, Zonghao Ying, Xianglong Liu, Dacheng Tao:
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing. CoRR abs/2510.01243 (2025) - 2024
- [j2]Dehong Kong, Siyuan Liang, Xiaopeng Zhu, Yuansheng Zhong, Wenqi Ren:
Patch is enough: naturalistic adversarial patch against vision-language pre-training models. Vis. Intell. 2(1): 33 (2024) - [c23]Xinwei Liu, Xiaojun Jia, Jindong Gu, Yuan Xun, Siyuan Liang, Xiaochun Cao:
Does Few-Shot Learning Suffer from Backdoor Attacks? AAAI 2024: 19893-19901 - [c22]Longkang Li, Siyuan Liang, Zihao Zhu, Chris Ding, Hongyuan Zha, Baoyuan Wu:
Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning. AAAI 2024: 20185-20193 - [c21]Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao:
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds. CVPR 2024: 24326-24335 - [c20]Siyuan Liang, Mingli Zhu, Aishan Liu, Baoyuan Wu, Xiaochun Cao, Ee-Chien Chang:
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning. CVPR 2024: 24645-24654 - [c19]Ruoyu Chen, Hua Zhang, Siyuan Liang, Jingzhi Li, Xiaochun Cao:
Less is More: Fewer Interpretable Region via Submodular Subset Selection. ICLR 2024 - [c18]Jiawei Liang, Siyuan Liang, Aishan Liu, Xiaojun Jia, Junhao Kuang, Xiaochun Cao:
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection. ICLR 2024 - [c17]Xianda Zhang, Siyuan Liang, Chengyang Li:
Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis. ICPR (24) 2024: 343-358 - [c16]Xinwei Zhang, Aishan Liu, Tianyuan Zhang, Siyuan Liang, Xianglong Liu:
Towards Robust Physical-world Backdoor Attacks on Lane Detection. ACM Multimedia 2024: 5131-5140 - [c15]Tianyuan Zhang, Lu Wang, Hainan Li, Yisong Xiao, Siyuan Liang, Aishan Liu, Xianglong Liu, Dacheng Tao:
LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions. ACM Multimedia 2024: 5403-5412 - [c14]Xinwei Liu, Xiaojun Jia, Yuan Xun, Siyuan Liang, Xiaochun Cao:
Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning. ACM Multimedia 2024: 8024-8033 - [c13]Mingli Zhu, Siyuan Liang, Baoyuan Wu:
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack. NeurIPS 2024 - [i42]Xinwei Liu, Xiaojun Jia, Jindong Gu, Yuan Xun, Siyuan Liang, Xiaochun Cao:
Does Few-shot Learning Suffer from Backdoor Attacks? CoRR abs/2401.01377 (2024) - [i41]Ruoyu Chen, Hua Zhang, Siyuan Liang, Jingzhi Li, Xiaochun Cao:
Less is More: Fewer Interpretable Region via Submodular Subset Selection. CoRR abs/2402.09164 (2024) - [i40]Jiawei Liang, Siyuan Liang, Aishan Liu, Xiaojun Jia, Junhao Kuang, Xiaochun Cao:
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection. CoRR abs/2402.11473 (2024) - [i39]Jiawei Liang, Siyuan Liang, Man Luo, Aishan Liu, Dongchen Han, Ee-Chien Chang, Xiaochun Cao:
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models. CoRR abs/2402.13851 (2024) - [i38]Xiaoxia Li, Siyuan Liang, Jiyi Zhang, Han Fang, Aishan Liu, Ee-Chien Chang:
Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs. CoRR abs/2402.14872 (2024) - [i37]Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao:
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds. CoRR abs/2403.05247 (2024) - [i36]Siyuan Liang, Kuanrong Liu, Jiajun Gong, Jiawei Liang, Yuan Xun, Ee-Chien Chang, Xiaochun Cao:
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning. CoRR abs/2403.16257 (2024) - [i35]Siyuan Liang, Wei Wang, Ruoyu Chen, Aishan Liu, Boxi Wu, Ee-Chien Chang, Xiaochun Cao, Dacheng Tao:
Object Detectors in the Open Environment: Challenges, Solutions, and Outlook. CoRR abs/2403.16271 (2024) - [i34]Xinwei Zhang, Aishan Liu, Tianyuan Zhang, Siyuan Liang, Xianglong Liu:
Towards Robust Physical-world Backdoor Attacks on Lane Detection. CoRR abs/2405.05553 (2024) - [i33]Dehong Kong, Siyuan Liang, Wenqi Ren:
Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection. CoRR abs/2405.07595 (2024) - [i32]Mingli Zhu, Siyuan Liang, Baoyuan Wu:
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack. CoRR abs/2405.16134 (2024) - [i31]Tianyuan Zhang, Lu Wang, Hainan Li, Yisong Xiao, Siyuan Liang, Aishan Liu, Xianglong Liu, Dacheng Tao:
LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions. CoRR abs/2406.00934 (2024) - [i30]Zonghao Ying, Aishan Liu, Tianyuan Zhang, Zhengmin Yu, Siyuan Liang, Xianglong Liu, Dacheng Tao:
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt. CoRR abs/2406.04031 (2024) - [i29]Siyuan Liang, Jiawei Liang, Tianyu Pang, Chao Du, Aishan Liu, Ee-Chien Chang, Xiaochun Cao:
Revisiting Backdoor Attacks against Large Vision-Language Models. CoRR abs/2406.18844 (2024) - [i28]Yisong Xiao, Aishan Liu, QianJia Cheng, Zhenfei Yin, Siyuan Liang, Jiapeng Li, Jing Shao, Xianglong Liu, Dacheng Tao:
GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing. CoRR abs/2407.00600 (2024) - [i27]Xinwei Liu, Xiaojun Jia, Yuan Xun, Siyuan Liang, Xiaochun Cao:
Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning. CoRR abs/2407.16307 (2024) - [i26]Aishan Liu, Yuguang Zhou, Xianglong Liu, Tianyuan Zhang, Siyuan Liang, Jiakai Wang, Yanjun Pu, Tianlin Li, Junqi Zhang, Wenbo Zhou, Qing Guo, Dacheng Tao:
Compromising Embodied Agents with Contextual Backdoor Attacks. CoRR abs/2408.02882 (2024) - [i25]Tianyuan Zhang, Lu Wang, Jiaqi Kang, Xinwei Zhang, Siyuan Liang, Yuwei Chen, Aishan Liu, Xianglong Liu:
Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving. CoRR abs/2409.07321 (2024) - [i24]Junhao Kuang, Siyuan Liang, Jiawei Liang, Kuanrong Liu, Xiaochun Cao:
Adversarial Backdoor Defense in CLIP. CoRR abs/2409.15968 (2024) - [i23]Yuan Xun, Siyuan Liang, Xiaojun Jia, Xinwei Liu, Xiaochun Cao:
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning. CoRR abs/2409.17601 (2024) - [i22]Kuanrong Liu, Siyuan Liang, Jiawei Liang, Pengwen Dai, Xiaochun Cao:
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats. CoRR abs/2409.19526 (2024) - [i21]Dehong Kong, Siyuan Liang, Xiaopeng Zhu, Yuansheng Zhong, Wenqi Ren:
Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models. CoRR abs/2410.04884 (2024) - [i20]Zheng Yi Ho, Siyuan Liang, Sen Zhang, Yibing Zhan, Dacheng Tao:
NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models. CoRR abs/2410.08970 (2024) - [i19]Zonghao Ying, Aishan Liu, Siyuan Liang, Lei Huang, Jinyang Guo, Wenbo Zhou, Xianglong Liu, Dacheng Tao:
SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models. CoRR abs/2410.18927 (2024) - [i18]Ruoyu Chen, Siyuan Liang, Jingzhi Li, Shiming Liu, Maosen Li, Zheng Huang, Hua Zhang, Xiaochun Cao:
Interpreting Object-level Foundation Models via Visual Precision Search. CoRR abs/2411.16198 (2024) - [i17]Tianyuan Zhang, Lu Wang, Xinwei Zhang, Yitong Zhang, Boyi Jia, Siyuan Liang, Shengshan Hu, Qiang Fu, Aishan Liu, Xianglong Liu:
Visual Adversarial Attack on Vision-Language Models for Autonomous Driving. CoRR abs/2411.18275 (2024) - [i16]Yisong Xiao, Aishan Liu, Xinwei Zhang, Tianyuan Zhang, Tianlin Li, Siyuan Liang, Xianglong Liu, Yang Liu, Dacheng Tao:
BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks. CoRR abs/2412.00746 (2024) - [i15]Zhixiang Guo, Siyuan Liang, Aishan Liu, Dacheng Tao:
CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models. CoRR abs/2412.01528 (2024) - [i14]Siyuan Liang, Jiajun Gong, Tianmeng Fang, Aishan Liu, Tao Wang, Xianglong Liu, Xiaochun Cao, Dacheng Tao, Ee-Chien Chang:
Red Pill and Blue Pill: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning. CoRR abs/2412.11471 (2024) - 2023
- [j1]Jingzhi Li, Hua Zhang, Siyuan Liang, Pengwen Dai, Xiaochun Cao:
Privacy-Enhancing Face Obfuscation Guided by Semantic-Aware Attribution Maps. IEEE Trans. Inf. Forensics Secur. 18: 3632-3646 (2023) - [c12]Bangyan He, Jian Liu, Yiming Li, Siyuan Liang, Jingzhi Li, Xiaojun Jia, Xiaochun Cao:
Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization. AAAI 2023: 764-772 - [c11]Chunyu Sun, Chenye Xu, Chengyuan Yao, Siyuan Liang, Yichao Wu, Ding Liang, Xianglong Liu, Aishan Liu:
Improving Robust Fariness via Balance Adversarial Training. AAAI 2023: 15161-15169 - [c10]Aishan Liu, Shiyu Tang, Siyuan Liang, Ruihao Gong, Boxi Wu, Xianglong Liu, Dacheng Tao:
Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization. CVPR 2023: 4096-4107 - [c9]Xin Dong, Rui Wang, Siyuan Liang, Aishan Liu, Lihua Jing:
Face Encryption via Frequency-Restricted Identity-Agnostic Attacks. ACM Multimedia 2023: 579-588 - [c8]Jiawei Liang, Siyuan Liang, Aishan Liu, Ke Ma, Jingzhi Li, Xiaochun Cao:
Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation. ACM Multimedia 2023: 768-778 - [c7]Jun Guo, Xingyu Zheng, Aishan Liu, Siyuan Liang, Yisong Xiao, Yichao Wu, Xianglong Liu:
Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks. ACM Multimedia 2023: 4178-4189 - [c6]Aishan Liu, Jun Guo, Jiakai Wang, Siyuan Liang, Renshuai Tao, Wenbo Zhou, Cong Liu, Xianglong Liu, Dacheng Tao:
X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection. USENIX Security Symposium 2023: 3781-3798 - [i13]Aishan Liu, Jun Guo, Jiakai Wang, Siyuan Liang, Renshuai Tao, Wenbo Zhou, Cong Liu, Xianglong Liu, Dacheng Tao:
X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection. CoRR abs/2302.09491 (2023) - [i12]Jun Guo, Aishan Liu, Xingyu Zheng, Siyuan Liang, Yisong Xiao, Yichao Wu, Xianglong Liu:
Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks. CoRR abs/2308.00958 (2023) - [i11]Bangyan He, Xiaojun Jia, Siyuan Liang, Tianrui Lou, Yang Liu, Xiaochun Cao:
SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation. CoRR abs/2312.04913 (2023) - [i10]Aishan Liu, Xinwei Zhang, Yisong Xiao, Yuguang Zhou, Siyuan Liang, Jiakai Wang, Xianglong Liu, Xiaochun Cao, Dacheng Tao:
Pre-trained Trojan Attacks for Visual Recognition. CoRR abs/2312.15172 (2023) - 2022
- [c5]Siyuan Liang, Longkang Li, Yanbo Fan, Xiaojun Jia, Jingzhi Li, Baoyuan Wu, Xiaochun Cao:
A Large-Scale Multiple-objective Method for Black-box Attack Against Object Detection. ECCV (4) 2022: 619-636 - [c4]Siyuan Liang, Aishan Liu, Jiawei Liang, Longkang Li, Yang Bai, Xiaochun Cao:
Imitated Detectors: Stealing Knowledge of Black-box Object Detectors. ACM Multimedia 2022: 4839-4847 - [i9]Siyuan Liang, Baoyuan Wu, Yanbo Fan, Xingxing Wei, Xiaochun Cao:
Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection. CoRR abs/2201.08970 (2022) - [i8]Yuhang Wang, Huafeng Shi, Rui Min, Ruijia Wu, Siyuan Liang, Yichao Wu, Ding Liang, Aishan Liu:
Adaptive Perturbation Generation for Multiple Backdoors Detection. CoRR abs/2209.05244 (2022) - [i7]Chunyu Sun, Chenye Xu, Chengyuan Yao, Siyuan Liang, Yichao Wu, Ding Liang, Xianglong Liu, Aishan Liu:
Improving Robust Fairness via Balance Adversarial Training. CoRR abs/2209.07534 (2022) - [i6]Siyuan Liang, Longkang Li, Yanbo Fan, Xiaojun Jia, Jingzhi Li, Baoyuan Wu, Xiaochun Cao:
A Large-scale Multiple-objective Method for Black-box Attack against Object Detection. CoRR abs/2209.07790 (2022) - [i5]Jiawei Liang, Siyuan Liang, Aishan Liu, Mingli Zhu, Danni Yuan, Chenye Xu, Xiaochun Cao:
Rethinking Data Augmentation in Knowledge Distillation for Object Detection. CoRR abs/2209.09841 (2022) - [i4]Shiyu Tang, Siyuan Liang, Ruihao Gong, Aishan Liu, Xianglong Liu, Dacheng Tao:
Exploring the Relationship between Architecture and Adversarially Robust Generalization. CoRR abs/2209.14105 (2022) - [i3]Longkang Li, Siyuan Liang, Zihao Zhu, Xiaochun Cao, Chris Ding, Hongyuan Zha, Baoyuan Wu:
Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning. CoRR abs/2210.17178 (2022) - 2021
- [c3]Siyuan Liang, Baoyuan Wu, Yanbo Fan, Xingxing Wei, Xiaochun Cao:
Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection. ICCV 2021: 7677-7687 - 2020
- [c2]Siyuan Liang, Xingxing Wei, Siyuan Yao, Xiaochun Cao:
Efficient Adversarial Attacks for Visual Object Tracking. ECCV (26) 2020: 34-50 - [i2]Siyuan Liang, Xingxing Wei, Siyuan Yao, Xiaochun Cao:
Efficient Adversarial Attacks for Visual Object Tracking. CoRR abs/2008.00217 (2020)
2010 – 2019
- 2019
- [c1]Xingxing Wei, Siyuan Liang, Ning Chen, Xiaochun Cao:
Transferable Adversarial Attacks for Image and Video Object Detection. IJCAI 2019: 954-960 - 2018
- [i1]Xingxing Wei, Siyuan Liang, Xiaochun Cao, Jun Zhu:
Transferable Adversarial Attacks for Image and Video Object Detection. CoRR abs/1811.12641 (2018)
Coauthor Index
[j16] [j13] [i85] [j12] [j11] [j4] [j3] [c38] [c37] [c35] [c32] [c28] [c25] [c24] [i75] [i74] [i71] [i69] [i68] [i66] [i64] [i62] [i60] [i57] [i55] [i49] [i48] [i47] [i46] [i45] [c23] [c21] [c20] [c19] [c18] [c14] [i42] [i41] [i40] [i39] [i37] [i36] [i35] [i29] [i27] [i24] [i23] [i22] [i18] [i14] [j1] [c12] [c8] [i11] [i10] [c5] [c4] [i9] [i6] [i5] [i3] [c3] [c2] [i2] [c1] [i1]
[j17] [j16] [j14] [j13] [c42] [c41] [j12] [j11] [j10] [j8] [j7] [j6] [j4] [c39] [c38] [c36] [c34] [c30] [c29] [c27] [c26] [c25] [i80] [i79] [i78] [i77] [i76] [i75] [i73] [i72] [i71] [i67] [i65] [i63] [i62] [i61] [i59] [i58] [i56] [i54] [i52] [i49] [i43] [c20] [c18] [c16] [c15] [i40] [i39] [i38] [i35] [i34] [i31] [i30] [i29] [i28] [i26] [i25] [i19] [i17] [i16] [i15] [i14] [c11] [c10] [c9] [c8] [c7] [c6] [i13] [i12] [i10] [c4] [i8] [i7] [i5] [i4]
[j18] [j17] [j16] [j14] [j13] [c42] [c40] [i89] [i88] [i87] [i86] [i84] [i83] [i82] [i81] [j12] [j10] [j8] [j7] [j6] [c39] [c38] [c36] [c34] [c31] [c30] [c29] [c26] [i80] [i79] [i78] [i77] [i73] [i71] [i70] [i69] [i67] [i65] [i63] [i61] [i56] [i44] [i43] [c15] [i35] [i31] [i30] [i28] [i26] [i20] [i19] [i16] [i15] [i14] [c10] [c6] [i13] [i10] [i4]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2026-07-23 22:55 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated, funded, and maintained by:
Schloss Dagstuhl - Leibniz Center for Informatics is a member of the Leibniz Association and is funded by the federal government of Germany and the states of Germany, especially Saarland and Rhineland‑Palatinate.
