AL
Aishan Liu
cs.CVcs.AIcs.CRcs.LGcs.CLcs.SEcs.RONeural Networks, ComputerAdversarial attackAlgorithmic testing
On Valency
published · living versionsW_qn3dhfa8·v1 · currentpublished
VagueBench: Benchmarking the Robustness of Embodied Agents on Ambient Context Illusions
with Yang Qu, Qiang Fu, Zonghao Ying, Jiayi Zhao +5
1 version
Preprints & journals
88 papers in the corpus · 2019–2026Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.42398000 · Zhang, Tianyuan, Liu, Xianglong, Liu, Aishan et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):13370-13388
Technical Report on the CVPR 2026@AdvML Workshop Challenge2607.11560v1 · Tianyuan Zhang, Zonglei Jing, Jiangfan Liu et al.2026 · 0 citationsarXiv
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners2606.18198v1 · Xiaojun Jia, Jie Liao, Simeng Qin et al.2026 · 0 citationsarXiv
Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models2604.05853v3 · Zonghao Ying, Haowen Dai, Lianyu Hu et al.2026 · 0 citationsarXiv
Ensemble-Based Uncertainty Estimation for Code Correctness Estimation2603.27098v2 · Yunxiang Wei, Tianlin Li, Yuwei Zheng et al.2026 · 0 citationsarXiv
M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation2512.22628v1 · Fanglin Xu, Wei Zhang, Jian Yang et al.2025 · 0 citationsarXiv
RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic2512.21220v2 · Le Wang, Zonghao Ying, Xiao Yang et al.2025 · 0 citationsarXiv
CodeSimpleQA: Scaling Factuality in Code Large Language Models2512.19424v1 · Jian Yang, Wei Zhang, Yizhi Li et al.2025 · 0 citationsarXiv
Scaling Laws for Code: Every Programming Language Matters2512.13472v1 · Jian Yang, Shawn Guo, Lin Jing et al.2025 · 0 citationsarXiv
SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment2511.13023v1 · Jiacheng Wang, Yejun Zeng, Jinyang Guo et al.2025 · 0 citationsarXiv
SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge2511.13127v3 · Zonghao Ying, Moyang Chen, Nizhang Li et al.2025 · 0 citationsarXiv
CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer2510.00501v3 · Kaixin Wang, Tianlin Li, Xiaoyu Zhang et al.2025 · 1 citationarXiv
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing2510.01243v1 · Yisong Xiao, Aishan Liu, Siyuan Liang et al.2025 · 0 citationsarXiv
From Context to Intent: Reasoning-Guided Function-Level Code Completion2508.09537v2 · Yanzhou Li, Tianlin Li, Yiran Zhang et al.2025 · 1 citationarXiv
MASteer: Multi-Agent Adaptive Steer Strategy for End-to-End LLM Trustworthiness Repair2508.06963v1 · Changqing Li, Tianlin Li, Xiaohan Zhang et al.2025 · 0 citationsarXiv
Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving2508.02028v2 · Tianyuan Zhang, Ting Jin, Lu Wang et al.2025 · 0 citationsarXiv
MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving2508.06534v3 · Aishan Liu, Jiakai Wang, Tianyuan Zhang et al.2025 · 0 citationsarXiv
PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation2508.01272v2 · Zonglei Jing, Xiao Yang, Xiaoqian Li et al.2025 · 0 citationsarXiv
Are AI Coders Snitches? An Empirical Study of Pretraining Data Detection on Code Large Language Models2507.17389v2 · Tianlin Li, Yunxiang Wei, Zhiming Li et al.2025 · 0 citationsarXiv
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks2507.01321v1 · Zhiyao Ren, Siyuan Liang, Aishan Liu et al.2025 · 0 citationsarXiv
Attacking cooperative multi-agent reinforcement learning by adversarial minority influence.40609504 · Li, Simin, Guo, Jun, Xiu, Jingqiao et al.2025 · 21 citationsNeural networks : the official journal of the International Neural Network Society. 2025;191:107747
ME: Trigger Element Combination Backdoor Attack on Copyright Infringement2506.10776v2 · Feiyu Yang, Siyuan Liang, Aishan Liu et al.2025 · 0 citationsarXiv
T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks2505.06679v2 · Jiayang Liu, Siyuan Liang, Shiqian Zhao et al.2025 · 0 citationsarXiv
T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models2504.15512v2 · Siyuan Liang, Jiayang Liu, Jiecheng Zhai et al.2025 · 2 citationsarXiv
Manipulating Multimodal Agents via Cross-Modal Prompt Injection2504.14348v4 · Le Wang, Zonghao Ying, Tianyuan Zhang et al.2025 · 8 citationsarXiv
Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models2504.07787v1 · Yisong Xiao, Aishan Liu, Siyuan Liang et al.2025 · 4 citationsarXiv
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework2503.16872v2 · Xuan Wang, Siyuan Liang, Dongping Liao et al.2025 · 0 citationsarXiv
Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings2503.15092v1 · Zonghao Ying, Guangyi Zheng, Yongxin Huang et al.2025 · 0 citationsarXiv
ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models2502.18511v1 · Xuxu Liu, Siyuan Liang, Mengya Han et al.2025 · 2 citationsarXiv
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models2502.11054v4 · Zonghao Ying, Deyue Zhang, Zonglei Jing et al.2025 · 6 citationsarXiv
Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving2501.13563v1 · Lu Wang, Tianyuan Zhang, Yang Qu et al.2025 · 0 citationsarXiv
CogMorph: Cognitive Morphing Attacks for Text-to-Image Models2501.11815v2 · Zonglei Jing, Zonghao Ying, Le Wang et al.2025 · 0 citationsarXiv
TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning2412.11471v2 · Siyuan Liang, Jiajun Gong, Tianmeng Fang et al.2024 · 0 citationsarXiv
PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models2412.07268v1 · Zining Wnag, Jinyang Guo, Ruihao Gong et al.2024 · 2 citationsarXiv
CopyrightShield: Enhancing Diffusion Model Security against Copyright Infringement Attacks2412.01528v2 · Zhixiang Guo, Siyuan Liang, Aishan Liu et al.2024 · 0 citationsarXiv
BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks2412.00746v1 · Yisong Xiao, Aishan Liu, Xinwei Zhang et al.2024 · 0 citationsarXiv
Visual Adversarial Attack on Vision-Language Models for Autonomous Driving2411.18275v2 · Tianyuan Zhang, Lu Wang, Xinwei Zhang et al.2024 · 4 citationsarXiv
LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment2410.21352v2 · Ge Yang, Changyi He, Jinyang Guo et al.2024 · 4 citationsarXiv
SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models2410.18927v1 · Zonghao Ying, Aishan Liu, Siyuan Liang et al.2024 · 17 citationsarXiv
Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving2409.07321v1 · Tianyuan Zhang, Lu Wang, Jiaqi Kang et al.2024 · 1 citationarXiv
GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models2408.12494v2 · Kunsheng Tang, Wenbo Zhou, Jie Zhang et al.2024 · 14 citationsarXiv
Compromising Embodied Agents with Contextual Backdoor Attacks2408.02882v1 · Aishan Liu, Yuguang Zhou, Xianglong Liu et al.2024 · 2 citationsarXiv
GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing2407.00600v1 · Yisong Xiao, Aishan Liu, QianJia Cheng et al.2024 · 0 citationsarXiv
Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift2406.18844v4 · Siyuan Liang, Jiawei Liang, Tianyu Pang et al.2024 · 15 citationsarXiv
Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks2406.06302v2 · Zonghao Ying, Aishan Liu, Xianglong Liu et al.2024 · 2 citationsarXiv
Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt2406.04031v2 · Zonghao Ying, Aishan Liu, Tianyuan Zhang et al.2024 · 29 citationsarXiv
LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions2406.00934v4 · Tianyuan Zhang, Lu Wang, Hainan Li et al.2024 · 8 citationsarXiv
Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography2405.14169v1 · Nhat Chung, Sensen Gao, Tuan-Anh Vu et al.2024 · 0 citationsarXiv
Towards Robust Physical-world Backdoor Attacks on Lane Detection2405.05553v3 · Xinwei Zhang, Aishan Liu, Tianyuan Zhang et al.2024 · 8 citationsarXiv
Object Detectors in the Open Environment: Challenges, Solutions, and Outlook2403.16271v4 · Siyuan Liang, Wei Wang, Ruoyu Chen et al.2024 · 2 citationsarXiv
Career total: 133 works. 88 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.