Mixed Strategy Game Model Against Data Poisoning Attacks
In this paper we use game theory to model poisoning attack scenarios. We prove the non-existence of pure strategy Nash Equilibrium in the attacker and defender game. We then propose a mixed extension of our game model and an algorithm to approximate the Nash Equilibrium strategy for the defender. We then demonstrate the effectiveness of the mixed defence strategy generated by the algorithm, in an experiment.
Code (0)
등록된 구현이 없습니다.
Tasks
Data PoisoningModel PoisoningSimilar Papers 제목 키워드 기반
Clean Label Attacks against SLU Systems
Poisoning backdoor attacks involve an adversary manipulating the training data to induce certain behaviors in the victim model by inserting a trigger in the signal at inference time. We adapted clean label backdoor (CLBD…
Data Poisoningspeech-recognitionSpeech RecognitionSpoken Language UnderstandingEfficient Adversarial Attacks on Online Multi-agent Reinforcement Learning
Due to the broad range of applications of multi-agent reinforcement learning (MARL), understanding the effects of adversarial attacks against MARL model is essential for the safe applications of this model. Motivated by …
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningMeta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
Federated learning (FL) is susceptible to a range of security threats. Although various defense mechanisms have been proposed, they are typically non-adaptive and tailored to specific types of attacks, leaving them insuf…
Federated LearningMeta-LearningModel PoisoningReinforcement Learning (RL)Stochastic Activation Pruning for Robust Adversarial Defense
Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, induce misclassification and threaten the reliability of deep learning sys…
Adversarial DefensePORE: Provably Robust Recommender Systems against Data Poisoning Attacks
Data poisoning attacks spoof a recommender system to make arbitrary, attacker-desired recommendations via injecting fake users with carefully crafted rating scores into the recommender system. We envision a cat-and-mouse…
Data PoisoningRecommendation Systems