TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint [1] (arXiv:2606.20553), demonstrates that a malicious parameter server can corrupt a PEFT adapter into a privacy backdoor: by assigning a dedicated memorization neuron to each training sample and ensuring each neuron updates at most once, the server can analytically reconstruct 59\%--79\% of client training data with high semantic fidelity. Existing defenses---including local differential privacy (LDP) [8] and gradient clipping---either fail against this attack or impose unacceptable utility degradation. We present \textbf{TriShield}, a three-layer deterministic defense that completely prevents NeuroImprint-style reconstruction with \textbf{zero model utility loss} and \textbf{no additional communication rounds}. TriShield consists of: (1) a \textbf{Parameter Artifact Detector} that identifies memory-neuron signatures in distributed model parameters before local training begins; (2) a \textbf{Stateful Virtual Iteration} mechanism that forces Adam/AdamW's momentum state to irreversibly entangle gradients across virtual steps, invalidating NeuroImprint's closed-form inversion; and (3) a \textbf{Zero-Utility Orthogonal Projection} operator that projects all local gradient updates onto the main-task semantic subspace computed via SVD, physically eliminating any gradient components that carry private memorization. We prove theoretically that after Layers 2 and 3, the mutual information between the uploaded gradient and any individual training sample is zero. Experiments on GPT-2 (117M) and Llama-Guard-3-1B verify that TriShield reduces NeuroImprint reconstruction rate to \textbf{0\%} across all tested attack variants, while maintaining or improving training accuracy, with less than 5\% additional GPU computation overhead.

Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Experts

The continuous scaling of large language models (LLMs) incurs prohibitive computational costs, making Mixture-of-Experts (MoE) a scalable alternative for efficient fine-tuning via sparse activation. While federated learning (FL) emerges as the paradigm for privacy-preserving collaborative optimization, integrating MoE into FL under data heterogeneity may trigger conflicting expert optimizations. Client-specific data distributions force same-indexed experts to optimize under inconsistent or even conflicting feature-label correlations. This mismatch induces destructive interference during aggregation, thus destabilizing the optimization trajectory and degrading model performance. To address this issue, we propose FC-MoE, a federated conflict-aware framework for MoE fine-tuning. It employs an importance aware weighting scheme to prioritize reliable local updates and utilizes gradient consensus projection to suppress conflicting updates, ensuring a stable global optimization path. Moreover, a local knowledge retention mechanism further preserves specialized client expertise by re-anchoring domain-specific residuals. Extensive experiments demonstrate that FC-MoE accelerates convergence and enhances both global and local model performance in non-IID federated environments.

PURGE: Projected Unlearning via Retain-Guided Erasure

We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems. CL tries to learn new tasks without forgetting old ones; MU tries to erase specific data without hurting retained performance representing the same underlying tension in opposite directions. PURGE leverages this duality by adapting gradient projection from A-GEM (Chaudhry et al., 2019) so that every unlearning step is constrained to not increase the retain-set loss. On top of this, it performs multi-layer representation erasure, pushing forget-set activations in intermediate layers towards the retain distribution to remove information from hidden representations rather than just suppressing it at the output. A key design choice is the retain-confusion target: rather than pushing forget outputs toward the uniform distribution, which we found to be surprisingly easy for membership inference attacks to detect, we instead target the model's natural confusion pattern on retain data. This makes the unlearned model hard to distinguish from one retrained from scratch. Two self-regulating stopping criteria (a retain-loss budget and a forget-accuracy target) let the algorithm decide on its own when to stop, removing the need for manual epoch tuning. In experiments on five datasets (CIFAR-10, MNIST, SVHN, STL10, PathMNIST) across 22 class-level forgetting tasks, PURGE consistently keeps retain accuracy above 96% while achieving MIA AUROC close to 0.5 (the ideal), outperforming gradient ascent, KL-uniform, and several published baselines on the privacy-utility frontier.