The paper introduces RASET, a router‑agnostic safety‑critical expert tuning framework for Mixture‑of‑Experts (MoE) large language models. RASET identifies a small subset of experts that are responsible for safety enforcement and applies parameter‑efficient tuning only to those experts, preserving the model’s intrinsic routing behavior. Experiments on five open‑weight MoE backbones show that RASET achieves a high safety‑bypass yield, outperforming existing baselines by a significant margin.
arXiv:2606. 00651v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dynamically routing inputs to relevant experts, yet introduce a critical vulnerability: Safety Sparsity, where safety capabilities concentrate in few experts, making them susceptible to adversarial bypassing.
arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.
arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.
The paper introduces GRIP, an algorithm‑agnostic framework for machine unlearning in Mixture‑of‑Experts large language models. GRIP enforces hard geometric constraints on router updates, projecting gradient changes into the null space of the retain set’s routing matrix to prevent routing manipulation. Two variants—training‑time stochastic projection and post‑training analytical correction—show significant improvements in routing stability, retain accuracy, and resistance to white‑box adversarial recovery across two MoE models.
The paper investigates why large language models lose safety alignment after benign fine‑tuning. It argues that safety alignment relies on a low‑rank, output‑routing geometry that becomes flatter during fine‑tuning, and that after only 100 benign examples this routing is sharpened in output‑side MLPs, leading to fragile safety while general performance remains relatively intact. Techniques like LoRA and ASAM can delay this collapse by reducing output‑side sharpness, but their effectiveness diminishes with larger fine‑tuning scales.
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.
The paper introduces RARE, a router‑agnostic representation engineering framework for Mixture‑of‑Experts language models. RARE projects behavioral perturbations onto the null space of the router matrix to avoid affecting routing, and corrects downstream routing drift. Experiments on six open‑weight MoE models show that RARE improves steering tasks—reducing harmfulness, increasing truthfulness, and enhancing factual editing—while preserving overall model accuracy.
arXiv:2607. 16242v1 Announce Type: cross Abstract: Fine-Tuning-as-a-Service (FTaaS) platforms let users train large language models (LLMs) on customized tasks, but this pipeline could erode models' safety alignment.
arXiv:2608. 02674v1 Announce Type: cross Abstract: With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward white-box attacks that directly identify and disrupt internal safety neurons or routes.
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
arXiv:2607. 11475v1 Announce Type: new Abstract: Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance.
arXiv:2607. 27081v1 Announce Type: cross Abstract: Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnerability: malicious data providers can embed harmful behaviors into downstream corpora, creating models that retain professional skills while violating human values on demand.