Skip to content
conftrace_

prompt attack

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

text-to-image generation (2) private information extraction (1) stealthiness (1) semantic-enhancing learning (1) sphere-probing learning (1) usability (1) crowd-sourced (1) defense-in-depth (1) multimodal retrieval-augmented generation (1) security analysis (1)

Papers

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation EMNLP 2025 Gandalf the Red: Adaptive Security for LLMs ICML 2025 Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models NeurIPS 2024 UPAM: Unified Prompt Attack in Text-to-Image Generation Models Against Both Textual Filters and Visual Checkers ICML 2024