1148 matches found
Towards Trustworthy Federated Learning with Untrusted Participants
Resilience against malicious participants and data privacy are essential for trustworthy federated learning, yet achieving both with good utility typically requires the strong assumption of a trusted central server. This paper shows that a significantly weaker assumption suffices: each pair of...
Secure and Private Federated Learning: Achieving Adversarial Resilience through Robust Aggregation
Federated Learning FL enables collaborative machine learning across decentralized data sources without sharing raw data. It offers a promising approach to privacy-preserving AI. However, FL remains vulnerable to adversarial threats from malicious participants, referred to as Byzantine clients, wh...
Poster: FedBlockParadox -- a Framework for Simulating and Securing Decentralized Federated Learning
A significant body of research in decentralized federated learning focuses on combining the privacy-preserving properties of federated learning with the resilience and transparency offered by blockchain-based systems. While these approaches are promising, they often lack flexible tools to evaluat...
Fingerprinting Deep Learning Models Via Network Traffic Patterns in Federated Learning
Federated Learning FL is increasingly adopted as a decentralized machine learning paradigm due to its capability to preserve data privacy by training models without centralizing user data. However, FL is susceptible to indirect privacy breaches via network traffic analysis-an area not explored in...
CSVAR: Enhancing Visual Privacy in Federated Learning Via Adaptive Shuffling against Overfitting
Although federated learning preserves training data within local privacy domains, the aggregated model parameters may still reveal private characteristics. This vulnerability stems from clients' limited training data, which predisposes models to overfitting. Such overfitting enables models to...
Shadow Defense against Gradient Inversion Attack in Federated Learning
Federated learning FL has emerged as a transformative framework for privacy-preserving distributed training, allowing clients to collaboratively train a global model without sharing their local data. This is especially crucial in sensitive fields like healthcare, where protecting patient data is...
Privacy-Preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models
Prompt learning is a crucial technique for adapting pre-trained multimodal language models MLLMs to user tasks. Federated prompt personalization FPP is further developed to address data heterogeneity and local overfitting, however, it exposes personalized prompts - valuable intellectual assets - ...
CADRE: Customizable Assurance of Data Readiness in Privacy-Preserving Federated Learning
Privacy-Preserving Federated Learning PPFL is a decentralized machine learning approach where multiple clients train a model collaboratively. PPFL preserves privacy and security of the client's data by not exchanging it. However, ensuring that data at each client is of high quality and ready for...
DP-RTFL: Differentially Private Resilient Temporal Federated Learning for Trustworthy AI in Regulated Industries
Federated Learning FL has emerged as a critical paradigm for enabling privacy-preserving machine learning, particularly in regulated sectors such as finance and healthcare. However, standard FL strategies often encounter significant operational challenges related to fault tolerance, system...
SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
Federated fine-tuning of large language models LLMs is critical for improving their performance in handling domain-specific tasks. However, prior work has shown that clients' private data can actually be recovered via gradient inversion attacks. Existing privacy preservation techniques against su...
Zero-Trust Foundation Models: a New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things
This paper focuses on Zero-Trust Foundation Models ZTFMs, a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models FMs for Internet of Things IoT systems. By integrating core tenets, such as continuous verification, least privilege access LPA, data...
Evaluating Query Efficiency and Accuracy of Transfer Learning-Based Model Extraction Attack in Federated Learning
Federated Learning FL is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property IP threats. Model extraction ME attacks pose a significant risk to Machine Learning as a Service MLaaS platforms, enabling attackers to replicate...
Toward Malicious Clients Detection in Federated Learning
Federated learning FL enables multiple clients to collaboratively train a global machine learning model without sharing their raw data. However, the decentralized nature of FL introduces vulnerabilities, particularly to poisoning attacks, where malicious clients manipulate their local models to...
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-2024-27254
IBM Db2 for Linux, UNIX and Windows includes DB2 Connect Server 10.5, 11.1, and 11.5 federated server is vulnerable to denial of service with a specially crafted query under certain conditions. IBM X-Force ID: 283813...
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-2023-28635
vantage6 is privacy preserving federated learning infrastructure. Prior to version 4.0.0, malicious users may try to get access to resources they are not allowed to see, by creating resources with integers as names. One example where this is a risk, is when users define which users are allowed to...
CVE-2023-30442
IBM Db2 for Linux, UNIX and Windows includes Db2 Connect Server 11.1 and 11.5 federated server is vulnerable to a denial of service as the server may crash when using a specially crafted wrapper using certain options. IBM X-Force ID: 253202...
CVE-2023-23929
vantage6 is a privacy preserving federated learning infrastructure for secure insight exchange. Currently, the refresh token is valid indefinitely. The refresh token should get a validity of 24-48 hours. A fix was released in version 3.8.0...