The paper introduces SEAL, a training-time, parameter‑efficient defense that attaches a plug‑and‑play adapter to the shared expert component of Mixture‑of‑Experts models, and SEAL++, which adds an orthogonal constraint to preserve existing safety subspaces. By leveraging the always‑activated shared expert, SEAL mitigates the structural vulnerability of sparse routing to adversarial manipulation, reducing attack success rates by up to 60% with minimal impact on model capability. The approach is evaluated across six attack scenarios involving harmful prompting, jailbreaks, malicious fine‑tuning, and neuron pruning.
By Qingyu Meng, Yiwei Zha, Jiahuan Pei, Koen Hindriks, Herbert Bos, Min Chen
The paper exposes a new vulnerability in Federated Retrieval-Augmented Generation (FedRAG) called Routing Hijacking, where a malicious client forges its semantic profile to attract target queries despite lacking relevant data. Experiments across three FedRAG routing architectures show that this attack consistently misroutes queries, causing downstream failures such as missing evidence, poisoning, incorrect answers, hallucinations, and sycophantic behavior. The authors propose a trust‑aware post‑routing framework that reweights clients based on evidence feedback, which effectively suppresses persistent hijacking and transfers to a learned neural router.
By Junjie Mu, Qiongxiu Li
arXiv:2606. 07857v1 Announce Type: cross Abstract: The rise of edge-based machine learning has enabled distributed adaptation of language models across mobile and IoT devices, offering privacy preservation and real-time responsiveness.
By Stefan Behfar, Richard Mortier
FedLNS is a server‑side framework that screens federated learning updates by representing each client’s contribution through changes in trainable normalization‑layer parameters, creating lightweight signatures that can be compared against a history‑aware cross‑client reference. The method requires no extra client‑to‑server communication, raw data, or labeled attack examples, and after screening, the remaining full‑model updates are aggregated with standard federated learning rules. Experiments on GPT‑style, BERT‑style, and LLaMA‑style models with 200 clients demonstrate that FedLNS achieves lower test perplexity than six baselines even when 40% of the population performs target manipulation under both IID and non‑IID data partitions.
By Kai Li, Jong-Ik Park, Carlee Joe-Wong, Wei Ni, Falko Dressler
arXiv:2604.27426v2 Announce Type: replace-cross
Abstract: Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although "local...
By Zi Li, Tian Zhou, Wenze Li, Jingyu Hua, Yunlong Mao, Sheng Zhong
RouteScan is a non‑intrusive auditing framework that detects harmful behavior in Mixture‑of‑Experts (MoE) large language models by analyzing expert‑routing telemetry captured from GPU execution. It uses the number of active GPU threads during the prefilling phase as a micro‑architectural fingerprint to isolate cross‑domain risk indicators and precisely identify malicious prompts. Evaluations on four open‑source MoE LLMs show strong generalization with AUROC > 0.91 on unseen harmful domains, while privacy tests indicate that full prompts cannot be reliably recovered from aggregated telemetry.
By Bo Lv, Zhiheng Xu, KeDong Xiu, Ruyi Ding, Tianhang Zheng, Zhibo Wang, Kui Ren
arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.
By Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas
FedGraph is a graph-based aggregation framework designed to defend federated large language model fine-tuning against backdoor attacks. It exploits the observation that malicious clients produce consistently similar updates, while benign clients generate diverse ones, by modeling client updates as nodes in a dynamically constructed graph and extracting structural features. The resulting compact client representations enable effective identification and suppression of malicious contributions, achieving high detection accuracy and low false positives in extensive experiments.
By Xi Chen, Chunyi Zhou, Rui Zeng, Xiaogang Xu, Zhe Liu, Shouling Ji
arXiv:2607. 13088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edge platforms.
By Ren-Yi Huang, Mingchen Li, Dumindu Samaraweera, Morris Chang
arXiv:2608. 12962v1 Announce Type: new Abstract: Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models.
By Ziqi Zhao, Jialin Lu, Junjie Shan, Junyuan Zhang, Shuya Yang, Ka-Ho Chow
arXiv:2606. 31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators.
By Seyed Bagher Hashemi Natanzi, Bo Tang
The paper introduces the Hop-Decayed Influence (HDI) attack, which targets auxiliary schema-level structures—semantic summaries, hierarchical edges, and pre-computed scores—used in GraphRAG pipelines for retrieval prioritisation. By propagating query-aware influence, HDI identifies high-impact targets and corrupts a minuscule fraction (as low as 0.016%) of these structures, achieving an 88–94% success rate across HotpotQA and 2WikiMultiHopQA benchmarks on Microsoft GraphRAG and HippoRAG2 architectures. The modifications affect up to six queries each, yielding a 1:N amplification that instance-level attacks cannot achieve, and they evade perplexity and paraphrase defenses with over 99% evasion, exposing a structural blind spot in current GraphRAG defenses.
By Jisung Park, John Le, Heath Cooper