发表机构
Atlassian（Atlassian公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出TSD-AUDIT框架，审计并强制基于图的向量检索中的遍历安全删除，解决仅输出安全可能遗漏过程级暴露的问题，显著提升区域删除下的召回率。
AI 中文摘要
检索增强系统日益依赖向量索引，而这些索引的搜索图可能保留已删除的条目。现有的删除接口可以防止已删除的标识符出现在返回结果中，但在图遍历过程中仍会计算其嵌入的距离。我们将这一区别形式化为输出安全与遍历安全，并引入TSD-AUDIT，一个用于审计和强制基于图的近似最近邻检索中遍历安全删除的框架。在Faiss IndexHNSWFlat上，原生过滤相对于未过滤搜索保持距离计算次数不变；在70%的删除率下，追踪回放检测到所有100个被审计查询中的已删除向量评分。对hnswlib的mark_deleted路径的代码检查揭示了相同的评分先于活性检查的模式。TSD-AUDIT强制执行活性先于评分的约束，仅使用活候选修复连接，并生成每个查询的评分追踪证书，独立验证者可根据删除快照进行检查。在区域定向删除下，TSD-AUDIT在删除比例从0.5到0.9时，相对于原生过滤将Recall@10提高了4.3至42.2个百分点，而在随机删除下保持相当。这些结果表明，仅输出删除审计可能遗漏过程级暴露：审计向量检索中的删除需要考虑搜索期间评分的向量，而不仅仅是返回的标识符。
英文摘要
Retrieval-augmented systems increasingly rely on vector indexes that may retain deleted items in their search graph. Existing deletion interfaces can prevent deleted identifiers from appearing in returned results while still computing distances to their embeddings during graph traversal. We formalize this distinction as output safety versus traversal safety, and introduce TSD-AUDIT, a framework for auditing and enforcing traversal-safe deletion in graph-based approximate nearest-neighbor retrieval. On Faiss IndexHNSWFlat, native filtering leaves the number of distance computations unchanged relative to unfiltered search; at a 70% deletion rate, trace-faithful replay detects deleted-vector scoring in all 100 audited queries. Code inspection of hnswlib's mark_deleted path reveals the same scoring-before-liveness pattern. TSD-AUDIT enforces an alive-before-scoring invariant, repairs connectivity using only live candidates, and emits per-query scored-trace certificates that an independent verifier can check against the deletion snapshot. Under region-targeted deletion, TSD-AUDIT improves Recall@10 over native filtering by 4.3--42.2 percentage points across deletion fractions from 0.5 to 0.9, while remaining comparable under random deletion. These results show that output-only deletion audits can miss process-level exposure: auditing deletion in vector retrieval requires accounting for the vectors scored during search, not only the identifiers returned.
