一篇新的研究论文发现，用于优化机器学习模型服务的动态量化技术存在严重漏洞。该漏洞被称为“Quantamination”，允许攻击者窃取同一处理批次中其他输入的敏感用户数据。该漏洞源于动态量化实现或配置不当所产生的侧信道，影响了至少四个流行的机器学习框架。 AI
影响 机器学习服务框架中潜在的数据泄露风险，要求对动态量化实现进行安全审计和修补。
排序理由 详细介绍机器学习框架中新发现漏洞的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
机器学习框架中的动态量化会泄露用户跨批次数据
报道来源 [2]
-
Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
arXiv:2604.26505v1 Announce Type: cross Abstract: Dynamic quantization emerged as a practical approach to increase the utilization and efficiency of the machine learning serving flow. Unlike static quantization, which applies quantization offline, dynamic quantization operates on…
-
Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
Dynamic quantization emerged as a practical approach to increase the utilization and efficiency of the machine learning serving flow. Unlike static quantization, which applies quantization offline, dynamic quantization operates on tensors at run-time, adapting its parameters to t…