Paper

Detecting and Mitigating Backdoor Attacks in OTA-FL Systems: A Two-Stage Robust Aggregation Scheme

Unreadunread

AI summary

arXiv:2605. 19253v1 Announce Type: new Abstract: Over-the-air federated learning (OTA-FL) improves communication efficiency by exploiting the superposition property of wireless channels, but this same property also creates a critical security vulnerability: the parameter server (PS) cannot access individual local updates, making it difficult to identify and exclude poisoned gradients.

Reading status

Priority

About this paper

Authors: Xiaoyan Ma, Seohyun Lee, Taejoon Kim, Christopher G. Brinton
Released: 2026-05-20 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because Detecting and Mitigating Backdoor Attacks in OTA-FL Systems: A Two-Stage Robust Aggregation Scheme overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, under, rate, trained, stage, position, model. Source: arxiv cs.CR (Cryptography and Security).
arXiv: 2605.19253

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Detecting and Mitigating Backdoor Attacks in OTA-FL Systems: A Two-Stage Robust Aggregation Scheme. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.