← Back to all news
arXiv AI By Pedro Beltr\'an-L\'opez, Enrique Tom\'as Mart\'inez Beltr\'an, Pantaleone Nespoli, Manuel Gil P\'erez, Alberto Huertas Celdr\'an

DecoyTrace: Toxic Decoys for Active Defense in Decentralized Federated Learning

Read the original on arXiv AI →

DecoyTrace is a proactive cyber‑deception defense designed for strictly serverless decentralized federated learning (DFL). It deploys mobile DecoyNodes that generate chaotic decoy challenges, disseminate dual models (clean vs. decoy) based on neighbor trust, and use three‑state semantic metrics to isolate malicious sources and recover models. Across sixty configurations on the NEBULA platform, DecoyTrace restores model utility with minimal performance loss and reduces CPU and network usage by up to two‑thirds.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 24

Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning

The paper introduces FedMAST, a Federated Multi‑Axis Structural Tracing defense designed to detect and contain backdoor attacks in federated learning. FedMAST evaluates client updates through complementary structural, spectral, and historical evidence, applying tiered filtering and round‑level containment. In experiments across six backdoor attacks, FedMAST consistently achieves lower attack success rates while preserving high main‑task accuracy.

By Srinivasan Subramanian, Kazi Aminul Islam, Md. Abdullah Al Hafiz Khan
multimodalsafety
More like this →
arXiv AI
Sep 24

When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense

The paper introduces Fed-ADR, a coordinated attack framework where a malicious orchestrator server directs heterogeneous adversarial clients to adapt their gradient updates in real time, thereby evading existing federated learning defenses and drastically reducing global model accuracy. It also presents a lightweight detection mechanism that estimates true client gradients from historical data to spot coordinated attacks, and an in-situ recovery method that restores model performance without restarting training. Experiments on MNIST, Fashion‑MNIST, and CIFAR‑10 show the attack can drop accuracy from over 90% to below 10%, while the defense can recover accuracy to above 90% within a few rounds at a computational cost at least 20× lower than retraining from scratch.

By Mohamed Shaaban, Ahmed Abdelnaby, Mohamed Elmahallawy
roboticsbenchmarkssafety
More like this →
arXiv AI
Jun 30

COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies

arXiv:2606. 30479v1 Announce Type: cross Abstract: Mitigating an observed adversary in an enterprise network typically takes weeks of expert work: an analyst derives a mitigation tailored to that adversary, validates it without breaking production, and verifies it disrupts the specific attack.

By Chen Frydman, Aviram Zilberman, Rubin Krief, Abed Showgan, Andres Murillo, Sekiya Motoyoshi, Asaf Shabtai, Yuval Elovici, Rami Puzis
llmsagents
More like this →