# vision-encoder
標記為「vision-encoder」的 4 篇文章
Adversarial Perturbation Attacks
Gradient-based pixel-level attacks against vision encoders, covering FGSM, PGD, C&W, transferability, physical-world adversarial examples, and perturbation budget constraints.
adversarial-perturbationsvision-encoderFGSMPGDtransferabilityVLMmultimodal
VLM Architecture & Vision-Language Alignment
Deep dive into VLM architectures including CLIP, SigLIP, and vision transformers. How image patches become tokens, alignment training, and where misalignment creates exploitable gaps.
vlmarchitecturevision-encodermultimodal
Adversarial Perturbation 攻擊s
Gradient-based pixel-level attacks against vision encoders, covering FGSM, PGD, C&W, transferability, physical-world adversarial examples, and perturbation budget constraints.
adversarial-perturbationsvision-encoderFGSMPGDtransferabilityVLMmultimodal
VLM 架構與視覺—語言對齊
深入探討 VLM 架構，包括 CLIP、SigLIP 與 vision transformers。圖像 patch 如何變成 token、對齊訓練，以及錯位（misalignment）如何製造可利用之缺口。
vlmarchitecturevision-encodermultimodal