all InfoSec news
Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models. (arXiv:2209.13523v2 [cs.LG] UPDATED)
Sept. 30, 2022, 1:20 a.m. | Raphael Olivier, Hadi Abdullah, Bhiksha Raj
cs.CR updates on arXiv.org arxiv.org
A targeted adversarial attack produces audio samples that can force an
Automatic Speech Recognition (ASR) system to output attacker-chosen text. To
exploit ASR models in real-world, black-box settings, an adversary can leverage
the transferability property, i.e. that an adversarial sample produced for a
proxy ASR can also fool a different remote ASR. However recent work has shown
that transferability against large ASR models is very difficult. In this work,
we show that modern ASR architectures, specifically ones based on
Self-Supervised …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Security Operations Analyst
@ Astranis | San Francisco
Manager - Business continuity Security and Safety.Risk and Compliance
@ MTN | Benin
Cyber Analyst, Digital Forensics Incident Response
@ At-Bay | Canada
Technical Product Manager, AppSec and DevSecOps
@ Penn Interactive | Philadelphia
Experienced Cloud Security Engineer (m/f/d) - Cybersecurity
@ MediaMarktSaturn | Barcelona, ES, 8003