Private Federated Learning Using Preference-Optimized Synthetic Data

In practical settings, differentially private Federated learning DP-FL is the dominant method for training models from private, on-device client data. Recent work has suggested that DP-FL may be enhanced or outperformed by methods that use DP synthetic data Wu et al., 2024; Hou et al., 2024. The...

TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification Utilizing OOD Data

Federated learning FL systems allow decentralized data-owning clients to jointly train a global model through uploading their locally trained updates to a centralized server. The property of decentralization enables adversaries to craft carefully designed backdoor updates to make the global model...

Towards Explainable and Lightweight AI for Real-Time Cyber Threat Hunting in Edge Networks

As cyber threats continue to evolve, securing edge networks has become increasingly challenging due to their distributed nature and resource limitations. Many AI-driven threat detection systems rely on complex deep learning models, which, despite their high accuracy, suffer from two major...

Local Data Quantity-Aware Weighted Averaging for Federated Learning with Dishonest Clients

Whitepaper called Local Data Quantity-Aware Weighted Averaging For Federated Learning With Dishonest Clients...

FLSSM: a Federated Learning Storage Security Model with Homomorphic Encryption

Federated learning based on homomorphic encryption has received widespread attention due to its high security and enhanced protection of user data privacy. However, the characteristics of encrypted computation lead to three challenging problems: "computation-efficiency", "attack-tracing" and...

CVE-2024-21649

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. Prior to 4.2.0, authenticated users could inject code into algorithm environment variables, resulting in remote code execution. This vulnerability is...

vantage6 安全漏洞

vantage6 is a vantage6 open source priVAcy preserviNg federalTed leArningG infrastructure for Secure Insight eXchange. A security vulnerability exists in versions of vantage6 prior to 4.5.0 that stems from the ability of collaboration administrators to add additional organizations to their...

CVE-2024-23823

CVE-2024-23823 affects the vantage6 server, where CORS restrictions are not enforced, allowing configured origins to be unrestricted. The vulnerability stems from overly permissive CORS settings in the open-source vantage6 framework for Federated Learning and MPC deployments. The limited impact i...

vantage6 Security Vulnerabilities

vantage6 is vantage6 open source an open source priVAcy preserviNg federalTed leArningG infrastructure for Secure Insight eXchange. A security vulnerability exists in versions of vantage6 prior to 4.2.1, which stems from an unrestricted CORS setting...

vantage6 Security Vulnerabilities

vantage6 is vantage6 open source an open source priVAcy preserviNg federalTed leArningG infrastructure for Secure Insight eXchange. A security vulnerability exists in vantage6 versions 4.2.0 and earlier that stems from not setting the security header...

CVE-2024-22193

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. There are no checks on whether the input is encrypted if a task is created in an encrypted collaboration. Therefore, a user may accidentally create a tas...

CVE-2024-21671

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. It is possible to find out usernames from the response time of login requests. This could aid attackers in credential attacks. Version 4.2.0 patches this...

CVE-2024-21653

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. Nodes and servers get a ssh config by default that permits root login with password authentication. In a proper deployment, the SSH service is not expose...

PYSEC-2024-30

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. Prior to 4.2.0, authenticated users could inject code into algorithm environment variables, resulting in remote code execution. This vulnerability is...

Design/Logic Flaw

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. There are no checks on whether the input is encrypted if a task is created in an encrypted collaboration. Therefore, a user may accidentally create a tas...

PYSEC-2024-31

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. It is possible to find out usernames from the response time of login requests. This could aid attackers in credential attacks. Version 4.2.0 patches this...

PYSEC-2024-30

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. Prior to 4.2.0, authenticated users could inject code into algorithm environment variables, resulting in remote code execution. This vulnerability is...

PYSEC-2024-32

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. There are no checks on whether the input is encrypted if a task is created in an encrypted collaboration. Therefore, a user may accidentally create a tas...

PYSEC-2024-33

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. Nodes and servers get a ssh config by default that permits root login with password authentication. In a proper deployment, the SSH service is not expose...

PYSEC-2024-31

The vantage6 technology enables to manage and deploy privacy enhancing technologies like Federated Learning FL and Multi-Party Computation MPC. It is possible to find out usernames from the response time of login requests. This could aid attackers in credential attacks. Version 4.2.0 patches this...