Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
Quantifying Return on Security Controls in LLM Systems
Richard Helder Moulton, Austin O'Brien, John D. Hastings
Although large language models (LLMs) are increasingly used in security-critical workflows, practitioners lack quantitative guidance on which safeguards are worth deploying. This p…
cs.CR2022
Detection and Prevention Against Poisoning Attacks in Federated Learning
Viktor Valadi, Madeleine Englund, Mark Spanier +1
This paper proposes and investigates a new approach for detecting and preventing several different types of poisoning attacks from affecting a centralized Federated Learning model…