Xinqi Lyu

4 papers · 2025–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

CVPR (3) ICCV (1)

Top co-authors

Bin Xiao (4) Dong Wang (3) Yihao Liu (2) Yiming Cao (1) Xiangyu He (1) Yanjie Li (1)

Research topics

Artificial Intelligence (4) Core AI (4) Computer Vision (1) Deep Learning (1) Machine Learning (1) Generation (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1)

Keywords

black-box attack (2) adversarial attack (2) prompt learning (1) safety alignment (1) multi-objective optimization (1) backdoor attack (1) text-to-image model (1) vision-language model (1) multimodal large language model (1) jailbreak attack (1) noise resilience (1) safety mechanism (1) targeted adversarial attack (1) prompt learning attack (1) retrieval-augmented diffusion model (1) adversarial red teaming (1) video prompting (1) knowledge base poisoning (1) adversarial learning (1) diffusion-based purification (1)

Papers

Breaking Multimodal LLM Safety via Video-Driven Prompting CVPR 2026 PureProof: Diffusion-Resistant Black-box Targeted Attack on Large Vision-Language Models CVPR 2026 Red-teaming Retrieval-Augmented Diffusion Models via Poisoning Knowledge Bases CVPR 2026 PLA: Prompt Learning Attack against Text-to-Image Generative Models ICCV 2025