#MachineLearningSecurity
Last but not least, came Tekgul & Asokan's "FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Masks" which is robust to model modification attacks. (www.acsac.org/2023/p...) 4/4
#MachineLearningSecurity #DeepReinforcementLearning #SecurityInAI
June 20, 2024 at 2:01 PM