Jinyuan Jia
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
arXiv 2026
HOComp: Interaction-Aware Human-Object Composition
arXiv 2025
AttnTrace: Attention-based Context Traceback for Long-Context LLMs
arXiv 2025
Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
arXiv 2025
TracLLM: A Generic Framework for Attributing Long Context LLMs
arXiv 2025
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
arXiv 2024
Certifiably Robust Image Watermark
arXiv 2024
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
CVPR 2024 1
FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models
arXiv 2024
Formalizing and Benchmarking Prompt Injection Attacks and Defenses
arXiv 2023
Affiliations
Frequent co-authors
10from 10 papers