WavePurifier: Purifying Audio Adversarial Examples via Hierarchical Diffusion Models

H Guo, G Wang, B Chen, Y Wang, X Zhang… - Proceedings of the 30th …, 2024 - dl.acm.org
In this paper, we propose WavePurifier, an audio purification framework to defend against
audio adversarial attacks. Audio adversarial attacks craft adversarial examples or …

From Compliance to Exploitation: Jailbreak Prompt Attacks on Multimodal LLMs

CW Chiu, L Huang, B Li, H Chen - arxiv preprint arxiv:2502.00735, 2025 - arxiv.org
Large Language Models (LLMs) have seen widespread applications across various
domains due to their growing ability to process diverse types of input data, including text …

AI を守るための防御的 AI ネットワークについて

岡島義憲, 山川宏 - 人工知能学会第二種研究会資料, 2024 - jstage.jst.go.jp
抄録 **年, 高度な自律型 AI の脆弱性に関する論文が急増し, 過去 AI 技術を先導してきた専門家
からの警告や提案も続いている. そこで, 本論では, それら脆弱性に関する議論の動向を攻撃手法や …