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…

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.

The paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing the backdoor generalizes at the token feature level, and proposes robust behavioral and weight-level detectors f…

This paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing that the resulting backdoor generalizes at the token feature level, and proposes robust behavioral and weight-l…

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…

This paper proposes FedDAB, a two-phase method for defending Federated Learning against backdoor attacks using local contrastive regularization and alignment checking.

The paper introduces Hidden Ads, a novel backdoor attack for Vision-Language Models (VLMs) that injects unauthorized advertisements by exploiting natural, recommendation-seeking user behaviors, mainta…

This paper systematically revisits and expands the threat model for backdoor attacks on semantic segmentation, proposing a unified framework (BADSEG) that demonstrates severe, previously overlooked vu…

This paper argues that much of the existing research on Federated Learning (FL) security is based on idealized assumptions, and provides a practical evaluation framework showing that real-world attack…

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…

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 proposes PRAETORIAN, a novel defense mechanism for Graph Neural Networks (GNNs) that targets the intrinsic structural requirements of backdoor attacks, significantly reducing the attack succ…

FedTrident proposes a comprehensive framework to defend Federated Learning-based Road Condition Classification against Targeted Label-Flipping Attacks, achieving robust performance comparable to non-a…

The paper proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

The paper introduces BadStyle, a novel backdoor attack framework that generates natural, stealthy poisoned samples using LLMs to compromise various LLMs with high success rates and robust activation.

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…

The paper introduces SET, a robust input-level backdoor detection framework that detects hidden malicious triggers in text-to-image diffusion models by analyzing systematic differences in how benign a…

This paper reinterprets catastrophic overfitting (CO) in Fast Adversarial Training (FAT) as a weak backdoor mechanism, proposing backdoor-inspired strategies to mitigate this generalization failure.

This paper introduces the Token by Token Backdoor Attack (ToBAC), demonstrating that unified autoregressive models (UAMs) are vulnerable to backdoor attacks where a single trigger can compromise multi…

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…