Securing distributed network digital twin systems against model poisoning attacks
In the era of 5G and beyond, the increasing complexity of wireless networks necessitates
innovative frameworks for efficient management and deployment. Digital twins (DTs) …
innovative frameworks for efficient management and deployment. Digital twins (DTs) …
Decaf: Data distribution decompose attack against federated learning
In contrast to prevalent Federated Learning (FL) privacy inference techniques such as
generative adversarial networks attacks, membership inference attacks, property inference …
generative adversarial networks attacks, membership inference attacks, property inference …
LoBAM: LoRA-Based Backdoor Attack on Model Merging
Model merging is an emerging technique that integrates multiple models fine-tuned on
different tasks to create a versatile model that excels in multiple domains. This scheme, in …
different tasks to create a versatile model that excels in multiple domains. This scheme, in …
Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning
Decentralized federated learning (DFL) is inherently vulnerable to poisoning attacks, as
malicious clients can transmit manipulated model gradients to neighboring clients. Existing …
malicious clients can transmit manipulated model gradients to neighboring clients. Existing …
On the Hardness of Decentralized Multi-Agent Policy Evaluation under Byzantine Attacks
In this paper, we study a fully-decentralized multi-agent policy evaluation problem, which is
an important sub-problem in cooperative multi-agent reinforcement learning, in the presence …
an important sub-problem in cooperative multi-agent reinforcement learning, in the presence …