all InfoSec news
Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners. (arXiv:2211.12990v1 [cs.LG])
Nov. 24, 2022, 2:10 a.m. | Elre T. Oldewage, John Bronskill, Richard E. Turner
cs.CR updates on arXiv.org arxiv.org
This paper examines the robustness of deployed few-shot meta-learning systems
when they are fed an imperceptibly perturbed few-shot dataset. We attack
amortized meta-learners, which allows us to craft colluding sets of inputs that
are tailored to fool the system's learning algorithm when used as training
data. Jointly crafted adversarial inputs might be expected to synergistically
manipulate a classifier, allowing for very strong data-poisoning attacks that
would be hard to detect. We show that in a white box setting, these attacks …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Technology Specialist II: Network Architect
@ Los Angeles County Employees Retirement Association (LACERA) | Pasadena, CA
Cybersecurity Skills Challenge -- Sponsored by DoD
@ Correlation One | United States
Security Operations Center (SOC) Analyst
@ GK Cybersecurity Group | Remote
Technical Writer Cybersecurity (Clearance Required)
@ ICF | Virginia Client Office (VA88)
Threat Management & Intelligence Expert (m/f/d)
@ METRO/MAKRO | Düsseldorf, Germany
IT Security Manager
@ Deutsche Telekom IT Solutions Slovakia | Košice, Slovakia (Slovak Republic)