Federated Learning Security Comparison Hub
5 papers - avg viability 6.0
Recent research in federated learning security is increasingly focused on enhancing resilience against adversarial attacks while maintaining privacy and efficiency. One promising direction involves integrating blockchain technology to create active defense mechanisms that bolster model integrity and data confidentiality. This approach not only addresses vulnerabilities inherent in decentralized training but also allows for adaptive responses to various attack strategies. Concurrently, the emergence of sophisticated adversarial techniques, such as distributed attacks that exploit structural nuances in model architectures, underscores the need for more nuanced defenses. Additionally, the looming threat of quantum computing has prompted the development of post-quantum cryptographic frameworks to safeguard collaborative threat intelligence sharing. These advancements signal a shift toward more robust, scalable solutions that prioritize both security and operational efficiency, making federated learning a more viable option for industries reliant on sensitive data, such as healthcare and finance.
Top Papers
- Resilient Federated Chain: Transforming Blockchain Consensus into an Active Defense Layer for Federated Learning(7.0)
Resilient Federated Chain leverages blockchain technology to bolster federated learning's resilience against adversarial attacks, ensuring secure decentralized training.
- Hide and Find: A Distributed Adversarial Attack on Federated Graph Learning(7.0)
FedShift is a stealthy and efficient adversarial attack method for federated graph learning, offering a robust solution for evaluating and improving the security of FedGL systems.
- Post-quantum Federated Learning: Secure And Scalable Threat Intelligence For Collaborative Cyber Defense(7.0)
A quantum-secure federated learning framework for collaborative threat intelligence, protecting cross-organizational data sharing against quantum attacks.
- Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning(7.0)
A lightweight architecture for verifiable aggregation in federated learning that enhances security without heavy cryptographic overhead.
- Structure-Aware Distributed Backdoor Attacks in Federated Learning(2.0)
Explore structure-aware defenses against backdoor attacks in federated learning.