Jinyuan Jia
Duke University
H-index: 23
North America-United States
Top articles of Jinyuan Jia
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models | Yanting Wang Hongye Fu Wei Zou Jinyuan Jia | 2024 | |
PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models | arXiv preprint arXiv:2402.07867 | Wei Zou Runpeng Geng Binghui Wang Jinyuan Jia | 2024/2/12 |
Pre-trained encoders in self-supervised learning improve secure and privacy-preserving supervised learning | Hongbin Liu Wenjie Qu Jinyuan Jia Neil Zhenqiang Gong | 2024 | |
GraphGuard: Provably Robust Graph Classification against Adversarial Attacks | Han Yang Binghui Wang Jinyuan Jia | 2024/2 | |
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning | Jinghuai Zhang Hongbin Liu Jinyuan Jia Neil Zhenqiang Gong | 2024 | |
TextGuard: Provable Defense against Backdoor Attacks on Text Classification | arXiv preprint arXiv:2311.11225 | Hengzhi Pei Jinyuan Jia Wenbo Guo Bo Li Dawn Song | 2023/11/19 |
Provably Robust Multi-bit Watermarking for AI-generated Text via Error Correction Code | arXiv preprint arXiv:2401.16820 | Wenjie Qu Dong Yin Zixin He Wei Zou Tianyang Tao | 2024/1/30 |
FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models | Yanting Wang Wei Zou Jinyuan Jia | 2024/4/12 | |
Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning | arXiv preprint arXiv:2401.05562 | Zhangchen Xu Fengqing Jiang Luyao Niu Jinyuan Jia Radha Poovendran | 2024/1/10 |
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding | arXiv preprint arXiv:2402.08983 | Zhangchen Xu Fengqing Jiang Luyao Niu Jinyuan Jia Bill Yuchen Lin | 2024/2/14 |
PORE: Provably Robust Recommender Systems against Data Poisoning Attacks | Jinyuan Jia Yupei Liu Yuepeng Hu Neil Zhenqiang Gong | 2023/3/26 | |
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI | 2023 Conference on Neural Information Processing Systems (NeurIPS '23) | Bochuan Cao Changjiang Li Ting Wang Jinyuan Jia Bo Li | 2023 |
Graph Contrastive Backdoor Attacks | Proceedings of the 40th International Conference on Machine Learning (ICML) | Hangfan Zhang Jinghui Chen Lu Lin Jinyuan Jia Dinghao Wu | 2023/7/23 |
Prompt Injection Attacks and Defenses in LLM-Integrated Applications | arXiv preprint arXiv:2310.12815 | Yupei Liu Yuqi Jia Runpeng Geng Jinyuan Jia Neil Zhenqiang Gong | 2023/10/19 |
FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information | Xiaoyu Cao Jinyuan Jia Zaixi Zhang Neil Zhenqiang Gong | 2023 | |
On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused? | arXiv preprint arXiv:2310.01581 | Hangfan Zhang Zhimeng Guo Huaisheng Zhu Bochuan Cao Lu Lin | 2023/10/2 |
FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning | Advances in Neural Information Processing Systems | Jinyuan Jia Zhuowen Yuan Dinuka Sahabandu Luyao Niu Arezoo Rajabi | 2024/2/13 |
REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service | Wenjie Qu Jinyuan Jia Neil Zhenqiang Gong | 2023/1/7 | |
Screen Perturbation: Adversarial Attack and Defense on Under-Screen Camera | Hanting Ye Guohao Lan Jinyuan Jia Qing Wang | 2023/10 | |
Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications | arXiv preprint arXiv:2311.16153 | Fengqing Jiang Zhangchen Xu Luyao Niu Boxin Wang Jinyuan Jia | 2023/11/7 |
