SecureSplit: Mitigating Backdoor Attacks in Split Learning

Split Learning SL offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset while maintaining distinct feature sets. However, SL is susceptible to backdoor attacks, in which malicious clients subtly alter their embeddings to...

Secure Wireless Communication Using Distributed Coherent Transmission and Spatial Signal Decomposition

We present a new approach to secure wireless communications using coherent distributed transmission of signals that are spatially decomposed between a two-element distributed antenna array. High-accuracy distributed coordination of microwave wireless systems supports the ability to transmit...

Enhancing Privacy in Decentralized Min-Max Optimization: a Differentially Private Approach

Decentralized min-max optimization allows multi-agent systems to collaboratively solve global min-max optimization problems by facilitating the exchange of model updates among neighboring agents, eliminating the need for a central server. However, sharing model updates in such systems carry a ris...

Non-Omniscient Backdoor Injection with a Single Poison Sample: Proving the One-Poison Hypothesis for Linear Regression and Linear Classification

Backdoor injection attacks are a threat to machine learning models that are trained on large data collected from untrusted sources; these attacks enable attackers to inject malicious behavior into the model that can be triggered by specially crafted inputs. Prior work has established bounds on th...

Malleability-Resistant Encrypted Control System with Disturbance Compensation and Real-Time Attack Detection

This study proposes an encrypted PID control system with a disturbance observer DOB using a keyed-homomorphic encryption KHE scheme, aiming to achieve control performance while providing resistance to malleability-based attacks. The controller integrates a DOB with a PID structure to compensate f...

SDD: Self-Degraded Defense against Malicious Fine-Tuning

Open-source Large Language Models LLMs often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To counter this, we theoretically uncover why malicious fine-tuni...

Backscattering-Based Security in Wireless Power Transfer Applied to Battery-Free BLE Sensors

The integration of security and energy efficiency in Internet of Things systems remains a critical challenge, particularly for battery-free and resource-constrained devices. This paper explores the scalability and protocol-agnostic nature of a backscattering-based security mechanism by integratin...

Accurate BGV Parameters Selection: Accounting for Secret and Public Key Dependencies in Average-Case Analysis

The Brakerski-Gentry-Vaikuntanathan BGV scheme is one of the most significant fully homomorphic encryption FHE schemes. It belongs to a class of FHE schemes whose security is based on the presumed intractability of the Learning with Errors LWE problem and its ring variant RLWE. Such schemes deal...

EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning

Despite federated learning FL's potential in collaborative learning, its performance has deteriorated due to the data heterogeneity of distributed users. Recently, clustered federated learning CFL has emerged to address this challenge by partitioning users into clusters according to their...

SmartAttack: Air-Gap Attack Via Smartwatches

Air-gapped systems are considered highly secure against data leaks due to their physical isolation from external networks. Despite this protection, ultrasonic communication has been demonstrated as an effective method for exfiltrating data from such systems. While smartphones have been extensivel...

Optimal Allocation of Privacy Budget on Hierarchical Data Release

Releasing useful information from datasets with hierarchical structures while preserving individual privacy presents a significant challenge. Standard privacy-preserving mechanisms, and in particular Differential Privacy, often require careful allocation of a finite privacy budget across differen...

Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks

Graph neural networks have been widely utilized to solve graph-related tasks because of their strong learning power in utilizing the local information of neighbors. However, recent studies on graph adversarial attacks have proven that current graph neural networks are not robust against malicious...

Benchmarking Differentially Private Tabular Data Synthesis

Differentially private DP tabular data synthesis generates artificial data that preserves the statistical properties of private data while safeguarding individual privacy. The emergence of diverse algorithms in recent years has introduced challenges in practical applications, such as inconsistent...