• I am a PhD student in Computer Science Department at Rutgers University. I am fortunate to be advised by Prof. Shiqing Ma and Prof. Dimitris N. Metaxas. I was a research scientist intern at GenAI@Meta, and a research intern at Sony AI.
• Research Interests: Generative Artificial Intelligence especially (Multimodal) Large Language Models; (M)LLM Post-training; (M)LLM Reasoning; (M)LLM-as-a-Judge; AI Safety; Responsible AIGC.

News

• [2025-02] 4 papers are accepted to CVPR 2025.
• [2025-01] 3 papers are accepted to ICLR 2025.
• [2025-01] 3 papers are accepted to NAACL 2025.

Publications

LLM Reasoning/LLM Post-training

• Token-Budget-Aware LLM Reasoning
  Tingxu Han*, Zhenting Wang*, Chunrong Fang, Shiyu Zhao, Shiqing Ma, Zhenyu Chen (Preprint, * indicates equal contribution)

• Visual Agents as Fast and Slow Thinkers
  Guangyan Sun, Mingyu Jin, Zhenting Wang, Cheng-Long Wang, Siqi Ma, Qifan Wang, Ying Nian Wu, Yongfeng Zhang, Dongfang Liu
  International Conference on Learning Representations 2024 (ICLR 2025)

• ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction
  Mingyu Jin, Haochen Xue, Zhenting Wang, Boming Kang, Ruosong Ye, Kaixiong Zhou, Mengnan Du, Yongfeng Zhang
  Conference on Language Modeling 2024 (COLM 2024)

• ProSec: Fortifying Code LLMs with Proactive Security Alignment
  Xiangzhe Xu, Zian Su, Jinyao Guo, Kaiyuan Zhang, Zhenting Wang, Xiangyu Zhang (Preprint)

• The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
  Zhuowei Li, Haizhou Shi, Yunhe Gao, Di Liu, Zhenting Wang, Yuxiao Chen, Ting Liu, Long Zhao, Hao Wang, Dimitris N. Metaxas (Preprint)

LLM-as-a-Judge

• MLLM-as-a-Judge for Image Safety without Human Labeling
  Zhenting Wang, Shuming Hu, Shiyu Zhao, Xiaowen Lin, Felix Juefei-Xu, Zhuowei Li, Ligong Han, Harihar Subramanyam, Li Chen, Jianfa Chen, Nan Jiang, Lingjuan Lyu, Shiqing Ma, Dimitris N. Metaxas, Ankit Jain
  IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR 2025)

Responsible Generative AI

• How to Trace Latent Generative Model Generated Images without Artificial Watermark?
  Zhenting Wang, Vikash Sehwag, Chen Chen, Lingjuan Lyu, Dimitris N. Metaxas, Shiqing Ma
  International Conference on Machine Learning 2024 (ICML 2024)

• DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
  Zhenting Wang, Chen Chen, Lingjuan Lyu, Dimitris N. Metaxas, Shiqing Ma
  International Conference on Learning Representations 2024 (ICLR 2024)

• Where Did I Come From? Origin Attribution of AI-Generated Images
  Zhenting Wang, Chen Chen, Yi Zeng, Lingjuan Lyu, Shiqing Ma
  Proceedings of Neural Information Processing Systems 2023 (NeurIPS 2023)

• Evaluating and Mitigating IP Infringement in Visual Generative AI
  Zhenting Wang, Chen Chen, Vikash Sehwag, Minzhou Pan, Lingjuan Lyu (Preprint)

• Continuous Concepts Removal in Text-to-image Diffusion Models
  Tingxu Han, Weisong Sun, Yanrong Hu, Chunrong Fang, Yonglong Zhang, Shiqing Ma, Tao Zheng, Zhenyu Chen, Zhenting Wang (Preprint)

• CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
  Siyuan Cheng, Lingjuan Lyu, Zhenting Wang, Xiangyu Zhang, Vikash Sehwag
  IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR 2025)

• Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
  Boheng Li, Yanhao Wei, Yankai Fu, Zhenting Wang, Yiming Li, Jie Zhang, Run Wang, Tianwei Zhang
  IEEE Symposiums on Security and Privacy 2025 (S&P 2025)

• Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
  Hanrong Zhang, Jingyuan Huang, Kai Mei, Yifei Yao, Zhenting Wang, Chenlu Zhan, Hongwei Wang, Yongfeng Zhang
  International Conference on Learning Representations 2024 (ICLR 2025)

• EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
  Sam Lin, Wenyue Hua, Zhenting Wang, Mingyu Jin, Lizhou Fan, Yongfeng Zhang
  Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics 2025 (NAACL 2025 Main)

• Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer
  Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, Chao Shen
  Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics 2025 (NAACL 2025 Findings)

• Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
  Minzhou Pan, Zhenting Wang, Xin Dong, Vikash Sehwag, Lingjuan Lyu, Xue Lin
  European Conference on Computer Vision 2024 (ECCV 2024)

• Robustness-aware Automatic Prompt Optimization
  Zeru Shi, Zhenting Wang, Yongye Su, Weidi Luo, Fan Yang, Yongfeng Zhang (Preprint)

• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
  Qingcheng Zeng, Mingyu Jin, Qinkai Yu, Zhenting Wang, Wenyue Hua, Zihao Zhou, Guangyan Sun, Yanda Meng, Shiqing Ma, Qifan Wang, Felix Juefei-Xu, Kaize Ding, Fan Yang, Ruixiang Tang, Yongfeng Zhang (Preprint)

AI Security

• Data-centric NLP Backdoor Defense from the Lens of Memorization
  Zhenting Wang, Zhizhi Wang, Mingyu Jin, Mengnan Du, Juan Zhai, Shiqing Ma
  Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics 2025 (NAACL 2025 Findings)

• Invisible Backdoor Attack against Self-supervised Learning
  Hanrong Zhang*, Zhenting Wang*, Boheng Li, Fulin Lin, Tingxu Han, Mingyu Jin, Chenlu Zhan, Mengnan Du, Hongwei Wang, Shiqing Ma
  IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR 2025, * indicates equal contribution)

• Distribution Preserving Backdoor Attack in Self-supervised Learning
  Guanhong Tao*,Zhenting Wang*,Shiwei Feng,Guangyu Shen,Shiqing Ma,Xiangyu Zhang
  IEEE Symposiums on Security and Privacy 2024
  (S&P 2024, * indicates equal contribution)

• UNICORN: A Unified Backdoor Trigger Inversion Framework
  Zhenting Wang, Kai Mei, Juan Zhai, Shiqing Ma
  International Conference on Learning Representations 2023 (ICLR 2023 Spotlight)

• Rethinking the Reverse-engineering of Trojan Triggers
  Zhenting Wang, Kai Mei, Hailun Ding, Juan Zhai, Shiqing Ma
  Proceedings of Neural Information Processing Systems 2022 (NeurIPS 2022)

• Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
  Zhenting Wang, Hailun Ding, Juan Zhai, Shiqing Ma
  Proceedings of Neural Information Processing Systems 2022 (NeurIPS 2022)

• BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning
  Zhenting Wang, Juan Zhai, Shiqing Ma
  IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022 (CVPR 2022)

• Exploring Inherent Backdoors in Deep Learning Models
  Guanhong Tao, Siyuan Cheng, Zhenting Wang, Shiqing Ma, Shengwei An, Yingqi Liu, Guangyu Shen, Zhuo Zhang, Yunshu Mao, Xiangyu Zhang
  Annual Computer Security Applications Conference 2024 (ACSAC 2024)

• NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
  Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang, Shiqing Ma
  Annual Meeting of the Association for Computational Linguistics 2023 (ACL 2023)

• Complex Backdoor Detection by Symmetric Feature Differencing
  Yingqi Liu, Guangyu Shen, Guanhong Tao, Zhenting Wang, Shiqing Ma, Xiangyu Zhang
  IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022 (CVPR 2022)

(Multimodal) Large Language Models

• Accelerating Multimodel Large Language Models by Searching Optimal Vision Token Reduction
  Shiyu Zhao, Zhenting Wang, Felix Juefei-Xu, Xide Xia, Miao Liu, Xiaofang Wang, Mingfu Liang, Ning Zhang, Dimitris N. Metaxas, Licheng Yu
  IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR 2025)

• Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?
  Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang (COLING 2025)

• Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities
  Hua Tang, Chong Zhang, Mingyu Jin, Qinkai Yu, Zhenting Wang, Xiaobo Jin, Yongfeng Zhang, Mengnan Du (SIGKDD Explorations 2024)

• LED: LLM Enhanced Open-Vocabulary Object Detection without Human Curated Data Generation
  Yang Zhou, Shiyu Zhao, Yuxiao Chen, Zhenting Wang, Dimitris N. Metaxas (Preprint)

• APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking
  Can Jin, Hongwu Peng, Shiyu Zhao, Zhenting Wang, Wujiang Xu, Ligong Han, Jiahui Zhao, Kai Zhong, Sanguthevar Rajasekaran, Dimitris N. Metaxas (Preprint)

• Health-LLM: Personalized Retrieval-Augmented Disease Prediction Model
  Mingyu Jin, Qinkai Yu, Dong Shu, Chong Zhang, Lizhou Fan, Wenyue Hua, Suiyuan Zhu, Yanda Meng, Zhenting Wang, Mengnan Du, Yongfeng Zhang (Preprint)

Computer Vision

• LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
  Can Jin, Ying Li, Mingyu Zhao, Shiyu Zhao, Zhenting Wang, Xiaoxiao He, Ligong Han, Tong Che, Dimitris N. Metaxas
  International Conference on Learning Representations 2024 (ICLR 2025)

• Learning Selective Assignment Network for Scene-aware Vehicle Detection
  Zhenting Wang, Wei Li, Xiao Wu, Luhan Sheng
  IEEE International Conference on Image Processing 2022 (ICIP 2022)

• CODAN: Counting-driven Attention Network for Vehicle Detection in Congested Scenes
  Wei Li, Zhenting Wang, Xiao Wu, Ji Zhang, Qiang Peng, Hongliang Li
  Proceedings of the 28th ACM International Conference on Multimedia (MM 2020 Oral)

Service

• Reviewer, International Conference on Learning Representations (ICLR), 2024, 2025
• Reviewer, International Conference on Machine Learning (ICML), 2022, 2023, 2024, 2025
• Reviewer, Conference on Neural Information Processing Systems (NeurIPS), 2022, 2023, 2024
• Reviewer, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 2024, 2025
• Reviewer, IEEE/CVF International Conference on Computer Vision (ICCV), 2023
• Reviewer, European Conference on Computer Vision (ECCV), 2024
• Reviewer, ACL Rolling Review (ARR), 2025
• Reviewer, International Conference on Artificial Intelligence and Statistics (AISTATS), 2025
• Reviewer, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023
• Reviewer, International World Wide Web Conference (WWW), 2025
• Reviewer, Annual AAAI Conference on Artificial Intelligence (AAAI), 2025
• Reviewer, International Joint Conference on Artificial Intelligence (IJCAI), 2023
• Reviewer, SIAM International Conference on Data Mining (SDM), 2024
• Reviewer, NeurIPS Dataset and Benchmark Track, 2024
• Reviewer, Backdoor Attacks and Defenses in Machine Learning Workshop (BANDS) at ICLR 2023
• Reviewer, Backdoors in Deep Learning - The Good, the Bad, and the Ugly (BUGS) at NeurIPS 2023
• Reviewer, IEEE Transactions on Information Forensics & Security (IEEE TIFS)
• Reviewer, IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)
• Reviewer, ACM Transactions on Knowledge Discovery from Data (ACM TKDD)
• Artifact Evaluation Committee, USENIX Security Symposium, 2022
• Sub-reviewer, ACM Conference on Computer and Communications Security (CCS), 2022, 2023, 2024
• Sub-reviewer, ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA), 2024

Teaching

• Guest Lecture, CS 431: Software Engineering, Rutgers University, Spring 2023
• Teaching Assistant, CS 461: Machine Learning Principles, Rutgers University, Fall 2024
• Teaching Assistant, CS 205: Introduction to Discrete Structures, Rutgers University, Fall 2022, Spring 2024
• Teaching Assistant, CS 213: Software Methodology, Rutgers University, Fall 2023
• Teaching Assistant, CS 431: Software Engineering, Rutgers University, Spring 2023