SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

Computer Science > Cryptography and Security [Submitted on 17 Apr 2026] SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models Noor Islam S. Mohammad, Uluğ Bayazıt Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety: privacy, security, misinformation, and adversarial robustness. SafeLM combines federated training with gradient smartification and Paillier encryption for privacy, integrates defenses against training and inference-time attacks, employs contrastive grounding with calibrated decoding to reduce hallucinations, and introduces alignment-aware binarized aggregation to enhance robustness while maintaining bounded reconstruction quality. Across benchmarks on factuality, toxicity, and membership inference, SafeLM achieves 98.0% harmful content detection accuracy, reduces communication by 96.9%, and lowers gradient inversion PSNR from 31.7 dB to 15.1 dB. Ablations show that each component contributes independently, whereas their integration yields a strong privacy utility efficiency trade-off for deploying trustworthy LLMs. Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2604.16606 [cs.CR]   (or arXiv:2604.16606v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.16606 Focus to learn more Submission history From: Noor Noor S. Mohammad [view email] [v1] Fri, 17 Apr 2026 18:00:58 UTC (161 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)