Abstract
Personal AI agents in enterprise multi-tenant deployments share a common vector store for long-term memory. Shared embedding spaces create a surface for cross-user memory leakage: a user's query can retrieve semantically adjacent memories belonging to another user through ordinary cosine-similarity retrieval, without any exploit. We formalize this as cross-user admissibility failure and evaluate it across six experiments, plus follow-up ablations, under both sparse (TF-IDF) and production-faithful (MiniLM-L6-v2) retrieval. Non-adversarial, incidental leakage reaches 70--100\% under pooled {same-team} retrieval; adversarially crafted memories achieve 90--100\% top-$k$ placement, exceeding weaker keyword-based attacker baselines, with score lifts of $+0.416$ to $+0.511$ under production-faithful dense retrieval (Config B); and end-to-end response contamination reaches 5.00/5 under a production retrieval path and 4.67/5 with Claude Sonnet~4.5, with contaminated responses often scoring as helpful or more helpful than clean ones, a gap validated against human judgment. Among three architectural mitigations, only hard post-retrieval ownership gating consistently restores the clean baseline (1.00/5) across {two generation models, at a measured latency overhead of roughly 1.4~ms per query.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Mudgal, P., Zhao, K., Zhang, G., Olsen, A., Miller, E., Chu, X., & Blanken, A. J. (2026). MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory. https://omanscience.com/en/articles/memleak-cross-user-semantic-leakage-in-multi-tenant-ai-agent-memory
MLA 9
Mudgal, Priyanka, et al. "MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory." https://omanscience.com/en/articles/memleak-cross-user-semantic-leakage-in-multi-tenant-ai-agent-memory.
Chicago (author–date)
Mudgal, Priyanka, Kai Zhao, Guilin Zhang, Andy Olsen, Ezekiel Miller, Xu Chu, and Aletta Johanna Blanken. 2026. "MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory." https://omanscience.com/en/articles/memleak-cross-user-semantic-leakage-in-multi-tenant-ai-agent-memory.
Harvard
Mudgal, P., Zhao, K., Zhang, G., Olsen, A., Miller, E., Chu, X. and Blanken, A. J. (2026) 'MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory', Available at: https://omanscience.com/en/articles/memleak-cross-user-semantic-leakage-in-multi-tenant-ai-agent-memory.
Vancouver
Mudgal P, Zhao K, Zhang G, Olsen A, Miller E, Chu X, et al. MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory. https://omanscience.com/en/articles/memleak-cross-user-semantic-leakage-in-multi-tenant-ai-agent-memory
IEEE
P. Mudgal, K. Zhao, G. Zhang, A. Olsen, E. Miller, X. Chu, and A. J. Blanken, "MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory," https://omanscience.com/en/articles/memleak-cross-user-semantic-leakage-in-multi-tenant-ai-agent-memory.