Web: http://arxiv.org/abs/2211.10024

Nov. 23, 2022, 2:20 a.m. | Stephen Casper, Kaivalya Hariharan, Dylan Hadfield-Menell

cs.CR updates on arXiv.org arxiv.org

Deep neural networks (DNNs) are powerful, but they can make mistakes that
pose significant risks. A model performing well on a test set does not imply
safety in deployment, so it is important to have additional tools to understand
its flaws. Adversarial examples can help reveal weaknesses, but they are often
difficult for a human to interpret or draw generalizable, actionable
conclusions from. Some previous works have addressed this by studying
human-interpretable attacks. We build on these with three contributions. …

attacks automated copy networks neural networks paste

Senior Cloud Security Engineer

@ HelloFresh | Berlin, Germany

Senior Security Engineer

@ Reverb | Remote, US

I.S. Security Analyst

@ YVFWC | Yakima, WA

Cybersecurity GRC Manager

@ Bitcoin Depot | Remote

Staff, Security Engineer (IT Infra Security Engineering)

@ Coupang | Seoul, South Korea

Principal DevSecOps Engineer (Remote)

@ Raft | Remote

Territory Account Manager - Cybersecurity - Baton Rogue

@ Optiv | Baton Rouge, LA

Analista de Segurança da Informação II (Application Security)

@ Loggi | São Paulo, State of São Paulo, Brazil - Remote

DevSecOps Solutions Architect Lead (AI/ML)

@ Rackner | United States

Senior Cryptography Engineer

@ Copper.co | Remote - UK and Europe

Security Research Manager

@ Nozomi Networks | Italy

Information Security Azure Expert (m/w/d)

@ Roland Berger | Munich, Germany