Skip to content
conftrace_

zero-shot method

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

compositional vulnerability (1) facial encoder (1) conditioning (1) discretization (1) latent speech feature (1) speaker-specific encoding (1) speech synthesis model (1) identity protection (1) portrait protection (1) pretrained vision-language model (1)

Papers

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates ACL 2025 IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation CVPR 2025 ELF: Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis ICML 2024