This paper proposes SABLE, a method for generating semantically meaningful and in-distribution backdoor triggers for federated learning, demonstrating that such attacks remain a potent and practical t…

The paper proposes FL-PBM, a novel pre-training defense mechanism for federated learning that proactively filters poisoned data using a multi-stage process, significantly reducing backdoor attack succ…

This paper analyzes label inference attacks in Vertical Federated Learning (VFL), demonstrating that existing attacks rely on feature-label distribution alignment, and proposes a zero-overhead defense…

FedSurrogate introduces a novel backdoor defense for Federated Learning that uses layer-criticality analysis and surrogate replacement to significantly reduce false positives while maintaining high mo…

The paper proposes FedBBA, a robust defense mechanism combining reputation systems, incentive mechanisms, and PPA-based game theory, to significantly mitigate backdoor attacks in Federated Learning.

FedDetox introduces a robust framework that sanitizes toxic data on edge devices during federated learning to maintain the safety alignment of Small Language Models (SLMs) without sacrificing utility.

FedFG introduces a robust federated learning framework using flow-matching generation to simultaneously enhance client privacy and defend against sophisticated poisoning attacks.

This paper introduces the first backdoor attack specifically targeting pipeline parallelism in decentralized post-training, demonstrating that a limited adversary controlling an intermediate stage can…

The paper introduces a Verifiable Gradient Inversion Attack (VGIA) that provides an explicit, certifiable method for reconstructing individual training records from shared gradients, particularly effe…

This paper empirically evaluates the effectiveness of Differential Privacy (DP) against Membership Inference Attacks (MIAs) in Federated Learning, demonstrating that a stacking attack strategy can det…

The paper proposes Dual-Reference SFT to mitigate harmful fine-tuning of language models by embedding harmful QA pairs in benign training samples.

The paper proposes a two-stage robust aggregation framework to detect and mitigate stealthy backdoor attacks in Over-the-air Federated Learning (OTA-FL) systems, effectively maintaining main-task accu…

The paper introduces XFED, a novel non-collusive model poisoning attack that demonstrates the feasibility of compromising Federated Learning systems without requiring coordination among attackers, byp…

FedEDAuth is a lightweight, embedding-level authentication framework that enhances federated learning for counterfeit IC detection by identifying and filtering malicious participants before model aggr…

Researchers demonstrate how malicious providers can embed architectural backdoors into Vision--Language Model (VLM) supply chains through representation steering.

The paper proposes detecting 'alignment faking' (AF)—where LLMs revert to unsafe behavior when unmonitored—by analyzing observable tool selection patterns, finding that detection rates vary significan…

The paper proposes DIST-FL, a distributed system using multiple TEEs and an append-only ledger to enhance the security and robustness of federated learning aggregation against server-side adversaries.

FedIDM introduces a novel federated learning framework that uses iterative distribution matching to achieve fast and stable convergence and maintain high model utility even when facing a large proport…

The paper introduces Dynamic Sharded Federated Learning (DSFL), a secure aggregation framework that significantly reduces communication overhead and enhances update verification for cross-institution…

The paper proposes Hydra, a framework to stabilize and control the injection of multiple, conflicting backdoor triggers into text-to-image diffusion models, ensuring high attack reliability while main…