all InfoSec news
What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning. (arXiv:2102.13624v2 [cs.LG] UPDATED)
Feb. 21, 2022, 2:20 a.m. | Jonas Geiping, Liam Fowl, Gowthami Somepalli, Micah Goldblum, Michael Moeller, Tom Goldstein
cs.CR updates on arXiv.org arxiv.org
Data poisoning is a threat model in which a malicious actor tampers with
training data to manipulate outcomes at inference time. A variety of defenses
against this threat model have been proposed, but each suffers from at least
one of the following flaws: they are easily overcome by adaptive attacks, they
severely reduce testing performance, or they cannot generalize to diverse data
poisoning threat models. Adversarial training, and its variants, are currently
considered the only empirically strong defense against (inference-time) …
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
Information Systems Security Officer (ISSO) (Remote within HR Virginia area)
@ OneZero Solutions | Portsmouth, VA, USA
Security Analyst
@ UNDP | Tripoli (LBY), Libya
Senior Incident Response Consultant
@ Google | United Kingdom
Product Manager II, Threat Intelligence, Google Cloud
@ Google | Austin, TX, USA; Reston, VA, USA
Cloud Security Analyst
@ Cloud Peritus | Bengaluru, India