Related papers: On Hyperparameters and Backdoor-Resistance in Hori…

Recently, backdoor attacks have become an emerging threat to the security of machine learning models. From the adversary's perspective, the implanted backdoors should be resistant to defensive algorithms, but some recently proposed…

Federated Learning (FL) enables collaborative deep learning training across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and the unvetted participants' data makes it vulnerable to…

Federated Learning (FL) is a collaborative machine learning technique where multiple clients work together with a central server to train a global model without sharing their private data. However, the distribution shift across non-IID…

This paper investigates the vulnerability of spiking neural networks (SNNs) and federated learning (FL) to backdoor attacks using neuromorphic data. Despite the efficiency of SNNs and the privacy advantages of FL, particularly in…

Context:With the advancement of artificial intelligence (AI) technology and applications, numerous AI models have been developed, leading to the emergence of open-source model hosting platforms like Hugging Face (HF). Thanks to these…

Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Vertical Federated Learning (VFL) focuses on handling vertically partitioned data over FL participants. Recent studies have discovered a significant vulnerability in VFL to backdoor attacks which specifically target the distinct…

Federated Learning (FL) is a decentralized learning approach that protects sensitive information by utilizing local model parameters rather than sharing clients' raw datasets. While this privacy-preserving method is widely employed across…

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…

As a key technology in 6G research, federated learning (FL) enables collaborative learning among multiple clients while ensuring individual data privacy. However, malicious attackers among the participating clients can intentionally tamper…

As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to eliminating the need for labeled data, research has found…

Federated learning (FL) is a distributed machine learning paradigm where enormous scattered clients (e.g. mobile devices or IoT devices) collaboratively train a model under the orchestration of a central server (e.g. service provider),…

Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method is particularly pertinent when entities possess datasets…

Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world…

This paper proposes adversarial attacks for Reinforcement Learning (RL) and then improves the robustness of Deep Reinforcement Learning algorithms (DRL) to parameter uncertainties with the help of these attacks. We show that even a naively…

Decentralized Federated Learning (DFL) remains highly vulnerable to adaptive backdoor attacks designed to bypass traditional passive defense metrics. To address this limitation, we shift the defensive paradigm toward a novel active,…

Federated learning (FL) attempts to train a global model by aggregating local models from distributed devices under the coordination of a central server. However, the existence of a large number of heterogeneous devices makes FL vulnerable…

Privacy-preserving federated learning (PPFL) aims to train a global model for multiple clients while maintaining their data privacy. However, current PPFL protocols exhibit one or more of the following insufficiencies: considerable…