Tao Qi

Venues

Frequent coauthors

Papers

1. Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models
   ACL 2026 ·

   Jinrui Wang

   DBLP profile ↗ORCID search ↗
2. Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
   ACL 2026 ·

   Peiru Yang

   DBLP profile ↗ORCID search ↗
3. Measuring Human Contribution in AI-Assisted Content Generation
   ACL 2026 ·

   Yueqi Xie

   DBLP profile ↗ORCID search ↗
4. MrM: Black-Box Membership Inference Attacks Against Multimodal RAG Systems
   AAAI 2026 ·

   Peiru Yang

   DBLP profile ↗ORCID search ↗
5. Robust Membership Inference for Large Language Models under Adversarial Generative Corruption
   ACL 2026 ·

   Yuanhong Huang

   DBLP profile ↗ORCID search ↗
6. ShieldRAG: Safeguarding Retrieval-Augmented Generation from Untrusted Knowledge Bases
   AAAI 2026 ·

   Peiru Yang

   DBLP profile ↗ORCID search ↗
7. Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
   NeurIPS 2025 ·

   Jinhua Yin

   DBLP profile ↗ORCID search ↗
8. From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning
   ICCV 2025 ·

   Hang Du

   DBLP profile ↗ORCID search ↗
9. Towards the Robustness of Differentially Private Federated Learning
   AAAI 2024 · Tao Qi