all InfoSec news
Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy
March 5, 2024, 3:11 p.m. | Jamie Hayes, Ilia Shumailov, Eleni Triantafillou, Amr Khalifa, Nicolas Papernot
cs.CR updates on arXiv.org arxiv.org
Abstract: The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a model has unlearned, an adversary that interacts with the model should no longer be able to tell whether the unlearned example was included in the model's training set or not. In the privacy literature, this is known as …
adversary arxiv cost cs.cr cs.lg high influence model training privacy remove techniques training
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Security Specialist
@ Nestlé | St. Louis, MO, US, 63164
Cybersecurity Analyst
@ Dana Incorporated | Pune, MH, IN, 411057
Sr. Application Security Engineer
@ CyberCube | United States
Linux DevSecOps Administrator (Remote)
@ Accenture Federal Services | Arlington, VA
Cyber Security Intern or Co-op
@ Langan | Parsippany, NJ, US, 07054-2172
Security Advocate - Application Security
@ Datadog | New York, USA, Remote