I am currently a Fourth Year Ph.D. Candidate at NESA Lab, advised by Prof. Shouling Ji. I received my B.S. degree with honors in Computer Science from Ningbo University (Yangming Class), advised by Prof. Diqun Yan. My research focuses on Trustworthy Generative AI in real-world applications, especially AI Security, AI Copyright Protection, and Privacy-Preserving AI. My long-term goal is to strengthen the source governance of AI technology and rectify illegal AI applications. Recently, I have been focusing more on the Security and Privacy risks of MLLMs, T2I models, and LLM Agents. Looking for undergraduate or graduate students with common research interests to collaborate with. Feel free to contact me by email or scan my WeChat QR code.

• Adversarial Attack: AAAI'25, ICMR'25 Oral, MASS'24, ICML'26
• Trojan Attack: ICME'25 Oral, ACL'25 Main, KDD'26, TIFS'26, ICML'26, TDSC'26 Submission, AAAI'27 Submission (Data Poisoning), AAAI'27 Submission (PRISM), KDD'27 Submission, NeurIPS'26 Submission
• Model Hijacking: AAAI'25, CCS'26, KDD'27 Submission
• LLM & MLLM Security: ICLR'26, KDD'26, EMNLP'26 Findings, MMM'26, Submission
• Agent Security: ICML'26, AAAI'27 Submission, Survey (Self-Evolving), Survey (Agentic Memory), Report

• Backdoor Defense: TDSC'25, Submission, Submission
• Privacy Protection: TDSC'25, MM'25, TIFS'26, MM'23, ECCV'26, ToN'26 Submission
• Data & Model Copyright: ICME'26, KDD'26 Oral, ICML'26, AAAI'27 Submission, Submission (Audio DeepFake Detection), Submission (Prompt Copyright)
• LLM & Agent Safety: CCS'26, TDSC'26, EMNLP'26 Findings, AAAI'27 Submission, Submission (T2I Content Safety)

• 2026.08: Our survey on Safety in Self-Evolving Agents is online!
• 2026.08: Our PoisonLoRA was selected as a poster at CCSC 2026!
• 2026.08: One paper was accepted by IEEE TDSC 2026, congratulations to Yiming!
• 2026.08: Two paper were accepted by EMNLP 2026 Findings, congratulations to all collaborators!
• 2026.07: One paper was accepted by ACM CCS 2026, congratulations to Professor Ma!
• 2026.06: One paper was accepted by ECCV 2026, congratulations to Yiming!
• 2026.05: One paper was accepted by ACM CCS 2026, congratulations to all collaborators!
• 2026.05: Two papers were accepted by KDD 2026, congratulations to all collaborators!
• 2026.05: Four papers were accepted by ICML 2026, congratulations to all collaborators!
• 2026.04: Our Report is online!
• 2026.03: The repositories of our Report and Survey are online!
• 2026.03: One paper was accepted by ICME 2026, congratulations to Xing!
• 2026.02: One paper was accepted by TIFS 2026, congratulations to Qianli!
• 2026.01: Two papers were accepted by ICLR 2026, congratulations to Linpei and Jianing!
• 2025.12: One paper was accepted by TIFS 2025, congratulations to God Ye!
• 2025.11: One paper was accepted by KDD 2026, congratulations to God Zhou!
• 2025.11: Our Trustworthy FL library (TFLlib) is open sourced!
• 2025.11: One paper was accepted by MMM 2026, congratulations to Junhao!
• 2025.08: One paper was accepted by TDSC 2025, congratulations to Professor Pu!
• 2025.07: One paper was accepted by MM 2025, congratulations to God Zhou!
• 2025.05: One paper was accepted by ACL 2025, congratulations to Xindi!
• 2025.04: One paper was accepted by TDSC 2025, congratulations to Professor Pu!
• 2025.04: One paper was accepted by ICMR 2025 Oral, congratulations to Zhiming!
• 2025.03: One paper was accepted by ICME 2025 Oral, congratulations to God Zhou!
• 2024.10: Two papers were accepted by AAAI 2025, congratulations to Xing!

($^\star$ denotes equal contribution; first/co-first-author papers are listed first) / Full list in Google Scholar

• Safety in Self-Evolving Agents: A Survey, Jiahao Chen, Zhou Feng, Oubo Ma, Yichen Yan, Ruixiao Lin, et al., Survey. PDF
• Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds, Jiahao Chen, Rui Yin, Xinfeng Li, Qianli Ma, Tianyu Du, Zhihui Fu, Jun Wang, Zhaoxiang Wang, Shouling Ji, EMNLP 2026 Findings. [CCF-B] Code
• Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystem, Jiahao Chen, Xing He, Yong Yang, Xinfeng Li, Chunyi Zhou, Junhao Li, Zhe Ma, Tianyu Du, and Shouling Ji, CCS 2026. [CCF-A] Code
• LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing, Jiahao Chen$^\star$, Junhao Li $^\star$, Yiming Wang, Yong Yang, Yi Jiang, Chunyi Zhou, Qingming Li, Tianyu Du, Shouling Ji, KDD 2026 Oral. [CCF-A] Code
• MADA-Attack: Transferable Multi-modal Attention Distraction Adversarial Attack against Vision Language Models, Zhihan Qin $^\star$, Jiahao Chen$^\star$, Chunyi Zhou, Yuwen Pu, Chunqiang Hu, Xiaolei Liu, Shouling Ji, ICML 2026. [CCF-A] Code
• Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data, Yuwen Pu $^\star$, Jiahao Chen $^\star$, Chunyi Zhou, Zhou Feng, Qingming Li, Chunqiang Hu and Shouling Ji, TDSC 2025. [CCF-A]
• Facial data minimization: Shallow model as your privacy filter, Yuwen Pu $^\star$, Jiahao Chen $^\star$, Jiayu Pan, Diqun Yan, Xuhong Zhang, Shouling Ji, TDSC 2025. [CCF-A]
• Poison in the Well: Feature Embedding Disruption in Backdoor Attacks, Zhou Feng $^\star$, Jiahao Chen $^\star$, Chunyi Zhou, Yuwen Pu, Qingming Li, Shouling Ji, ICME 2025 Oral. [CCF-B]
• Enhancing Adversarial Transferability with Adversarial Weight Tuning, Jiahao Chen $^\star$, Zhou Feng $^\star$, Rui Zeng, Yuwen Pu, Chunyi Zhou, Yi Jiang, Yuyou Gan, Jinbao Li, Shouling Ji, AAAI 2025. [CCF-A] Code
• CAMH: Advancing Model Hijacking Attack in Machine Learning, Xing He $^\star$, Jiahao Chen $^\star$, Yuwen Pu, Qingming Li, Chunyi Zhou, Yingcai Wu, Jinbao Li, Shouling Ji, AAAI 2025. [CCF-A] Code
• Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models, Fengheng Chu, Jiahao Chen, Yuhong Wang, Jun Wang, Zhihui Fu, Shouling Ji, Lu Dong, Songze Li, EMNLP 2026 Findings. [CCF-B]
• FaceArmor: A Universal Facial Image Protection Against Diffusion-Based Manipulations, Yiming Wang, Jiahao Chen, Qingming Li, Chunyi Zhou, Zhi Chen, Lingzhong Meng, Jinbao Li, Shouling Ji, ECCV 2026. [CCF-B]
• IntraGuard: Committee-Side Defenses Against Review Outsourcing to Commercial Chatbots, Oubo Ma, Ruixiao Lin, Jiahao Chen, Yuan Su, Yong Yang, Shouling Ji, CCS 2026. [CCF-A] Code
• AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models, Yiming Wang, Jiahao Chen, Qingming Li, Tong Zhang, Rui Zeng, Xing Yang, Shouling Ji, TDSC 2026. [CCF-A]
• The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrails, Shuo Shi, Rui Yin, Naen Xu, Jiahao Chen, Chunyi Zhou, Tianyu Du, Zhihui Fu, Jun Wang, Zhaoxiang Wang, Shouling Ji, KDD 2026. [CCF-A] Code
• The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attacks, Zhou Feng, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Tianyu Du, Jinbao Li, Jianhai Chen, Shouling Ji, KDD 2026. [CCF-A] Code
• Order within Chaos: Capturing Intrinsic Energy Anomalies for AI-Manipulated Image Forgery Localization, Yiming Wang, Baiqi Wu, Qingming Li, Jiahao Chen, Tong Zhang, Shouling Ji, ICML 2026. [CCF-A] Code
• SOPE: Situation-Aware and Statistically Indistinguishable Privacy Exfiltration for MCP-enabled Agents, Ruixiao Lin, Qingming Li, Jiahao Chen, Chunyi Zhou, Shouling Ji, ICML 2026. [CCF-A]
• Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning, Oubo Ma, Ruixiao Lin, Yang Dai, Jiahao Chen, Chunyi Zhou, Linkang Du, Shouling Ji, ICML 2026. [CCF-A] Code
• LoRA-Hash: Unveiling Model Identity from Heavy-Tailed Weight Distributions, Xing He, Jiahao Chen, Junhao Li, Feng Zhou, Shouling Ji, ICME 2026. [CCF-B]
• DUAP: Disentanglement-based Universal Adversarial Perturbations for Robust Multilingual Speech Privacy Protection, Qianli Ma, Wenjie Zhang, Jiahao Chen, et al., TIFS 2026. [CCF-A]
• STAR: Strategy-driven Automatic Jailbreak Red-teaming For Large Language Model, Jianing Liu, Qingming Li, Jiahao Chen, Rui Zeng, Binbin Zhao, Shouling Ji, ICLR 2026. [CCF-A] Code
• Contextual and Seasonal LSTMs for Time Series Anomaly Detection, Lingpei Zhang, Qingming Li, Yong Yang, Jiahao Chen, Rui Zeng, Chenyang Lyu, Shouling Ji, ICLR 2026. [CCF-A]
• Auditing M-LLMs for Privacy Risks: A Synthetic Benchmark and Evaluation Framework, Junhao Li, Jiahao Chen, Zhou Feng, Chunyi Zhou, MMM 2026. [CCF-C] Code
• StealthPhase: Towards a Stealthy Backdoor Attack Against Speaker Recognition, Zhe Ye, Qiben Yan, Jiahao Chen, Xiangui Kang, and Jiwu Huang, TIFS 2025. [CCF-A]
• Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakes, Zhou Feng, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Qingming Li, Tianyu Du, Shouling Ji, MM 2025. [CCF-A] Code
• TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image Models, Xindi Li, Zhe Liu, Tong Zhang, Jiahao Chen, Qingming Li, Jinbao Li, Shouling Ji, ACL 2025 Main. [CCF-A]
• Enhancing Adversarial Transferability via Self-Ensemble Feature Alignment, Zhiming Zhao, Jiahao Chen, Qingming Li, Chunyi Zhou, Shouling Ji, ICMR 2025 Oral. [CCF-B]
• AdvUSL: Targeted Adversarial Attack against U-shaped Split Learning, Yunxiao He, Chunqiang Hu, Yuwen Pu, Jiahao Chen, Xingwang Li, MASS 2024. [CCF-C]
• Universal defensive underpainting patch: Making your text invisible to optical character recognition, JiaCheng Deng, Li Dong, Jiahao Chen, Diqun Yan, Rangding Wang, Dengpan Ye, Lingchen Zhao, Jinyu Tian, ACM MM 2023. [CCF-A] Code

• 2025.12 2nd PhD Program of the Young S&T Talents Cultivation Project, CAST (中国科协青年科技人才培育工程博士生专项计划).

• 2023.09 - now, Ph.D. Candidate, Electronic Information, College of Computer Science and Technology, Zhejiang University.
• 2019.09 - 2023.06, B.E., Computer Science, YangMing College, Ningbo University.

• Conference Reviewers: NeurIPS, ICLR, ICML, CVPR, ECCV, KDD, ACL, AAAI, ACM MM, AAMAS, GlobeCom, SaTML
• Journal Reviewers: TDSC, TIFS, TASLP, Neural Networks

• 2023.05 - 2025.07, Ant Group, Hangzhou.
• 2025.07 - 2026.07, OPPO Research Institute, ShenZhen.
• 2026.08 - Now, Alibaba Security, Hangzhou. Research on Agent Security.