羊の皮を被ったピクセル:HDRゲインマップを悪用した視覚カモフラージュ攻撃
A Wolf in Sheep's Pixels: Visual Camouflage Attacks via HDR Gain Maps
HDR表示のゲインマップ再構成を逆手に取り、1枚のJPEGにSDRベースと異なるHDR画像を埋め込み、自動モデレーションを回避しつつ人間には有害コンテンツを見せる攻撃DRJanusを提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Qi Shen, Yujia Gong, Yue Zhao, Tong Liu
分類: cs.CV, cs.AI
原文アブストラクト
An image can pass automated safety checks while showing harmful content to its human viewer. We introduce DRJanus, a visual camouflage attack that exploits the gap between standard dynamic range (SDR) processing and high dynamic range (HDR) display. Automated systems often read only an image's SDR base, whereas HDR viewers reconstruct its appearance using an auxiliary gain map. DRJanus inverts this reconstruction to embed two independently chosen color images in a single JPEG, without querying or optimizing against the target model. It preserves the chosen SDR base exactly and reconstructs HDR targets at an average PSNR of 43.03 dB across 400 images. On a benchmark of 100 sexual-content images, DRJanus evades detection by all six tested commercial moderation services and nine vision-language models. Across five agents, each evaluated on 120 task cases per threat setting, attack success ranges from 31.67% to 100% for moderation evasion and from 95% to 100% for task manipulation. We also explore cross-view consistency checks as a mitigation. These findings expose a gap in visual trust: securing what a machine reads does not secure what a user sees. A demo is available at https://qshen0629.github.io/DRJanus/
