# pruning
標記為「pruning」的 6 篇文章
Model Compression Security
Security implications of model pruning, quantization, and knowledge distillation on AI system robustness.
infrastructuremodel-compressionpruningquantizationdistillation
Inference Optimization Risks
Security implications of model optimization techniques — covering quantization safety degradation, pruning vulnerability introduction, distillation attacks, and speculative decoding risks.
quantizationpruningdistillationoptimizationinferencesafety-degradation
Pruning Impact on Safety
How structured and unstructured pruning affects model safety properties, and techniques for exploiting pruning artifacts to bypass safety training.
modelspruningsparsitysafety
模型 Compression 安全
安全 implications of model pruning, quantization, and knowledge distillation on AI system robustness.
infrastructuremodel-compressionpruningquantizationdistillation
推論最佳化風險
模型最佳化技術的安全意涵——涵蓋量化安全降級、剪枝漏洞引入、蒸餾攻擊與推測解碼風險。
quantizationpruningdistillationoptimizationinferencesafety-degradation
Pruning Impact on Safety
How structured and unstructured pruning affects model safety properties, and techniques for exploiting pruning artifacts to bypass safety training.
modelspruningsparsitysafety