all AI news
Adversarial Illusions in Multi-Modal Embeddings
Feb. 20, 2024, 5:45 a.m. | Tingwei Zhang, Rishi Jha, Eugene Bagdasaryan, Vitaly Shmatikov
cs.LG updates on arXiv.org arxiv.org
Abstract: Multi-modal embeddings encode texts, images, sounds, videos, etc., into a single embedding space, aligning representations across different modalities (e.g., associate an image of a dog with a barking sound). In this paper, we show that multi-modal embeddings can be vulnerable to an attack we call "adversarial illusions." Given an image or a sound, an adversary can perturb it to make its embedding close to an arbitrary, adversary-chosen input in another modality.
These attacks are cross-modal …
abstract adversarial arxiv call cs.ai cs.cr cs.lg dog embedding embeddings encode etc image images modal multi-modal paper show sound space type videos vulnerable
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US