mlsanityData to 14 Oct 2026

STAIN-FL: Stealthy Targeted Attack Injection with Contextual Triggers in Federated Learning

arXiv 2608.23952 ↗First posted 25 Aug 2026cs.CR cs.AIcited by 0

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Federated video anomaly detection trains model collaboratively without sharing raw surveillance footage, but limited server-side visibility lets compromised clients to inject backdoor via malicious updates. This paper introduces STAIN-FL, a stealthy targeted backdoor attack injection framework that uses naturally occurring surveillance conditions, including low-light scenes, indoor settings, and crowd density, as contextual triggers. STAIN-FL combines anomaly-to-benign label textitmanipulation with gradient masking over least-updated coordinates to preserve clean accuracy while inducing trigger-conditioned misclassification. We evaluate STAIN-FL on textttUCF-Crime using 1024-dimensional I3D features in a non-IID four-client multi-agency setting, comparing FedAvg and FedProx under sparse and continuous attacks. Results show that sparse attacks have low-detectability, operationally significant attacks rather than high-intensity attacks: they keep the mean clean-accuracy drop below 2%, yet still misclassify more than half of triggered anomalies at peak backdoor accuracy under FedAvg (56.7%) and FedProx (54.2%). Under FedAvg, the sparse backdoor remains above the 25% backdoor-accuracy threshold for an average of 336 post-attack rounds, highlighting the persistence risk of contextually triggered attacks in surveillance systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 7 of its 11 references that are in the map. First posted on arXiv 25 Aug 2026.

Builds on

7 of 11 references.

References · 7

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  4. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
  5. 2024Collaborative Learning of Anomalies with Privacy (CLAP) for Unsupervised Video Anomaly Detection: A New Baselinecited by 17
  6. 2024Cross-Context Backdoor Attacks against Graph Prompt Learningcited by 14
  7. 2024SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning
  2. 2025Multi-Target Federated Backdoor Attack Based on Feature Aggregation
  3. 2025SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
  4. 2026Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks
  5. 2025Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis
  6. 2025Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
  7. 2023FTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learning
  8. 2025Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction