all InfoSec news
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models
March 29, 2024, 4:11 a.m. | Yanting Wang, Hongye Fu, Wei Zou, Jinyuan Jia
cs.CR updates on arXiv.org arxiv.org
Abstract: Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D points, audio, text, etc. Similar to unimodal models, many existing studies show that a multi-modal model is also vulnerable to adversarial perturbation, where an attacker could add small perturbation to all modalities of a multi-modal input such that the multi-modal model makes incorrect predictions for it. …
adversarial adversarial attacks arxiv attacks audio called cs.cr cs.cv defense etc image input modal points single studies text
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Senior Security Engineer - Detection and Response
@ Fastly, Inc. | US (Remote)
Application Security Engineer
@ Solidigm | Zapopan, Mexico
Defensive Cyber Operations Engineer-Mid
@ ISYS Technologies | Aurora, CO, United States
Manager, Information Security GRC
@ OneTrust | Atlanta, Georgia
Senior Information Security Analyst | IAM
@ EBANX | Curitiba or São Paulo
Senior Information Security Engineer, Cloud Vulnerability Research
@ Google | New York City, USA; New York, USA