AI & ML
When Shuffling Fails: Token Recovery from Obfuscated KV Caches
arXiv cs.CR0 views
arXiv:2611.24276v1 Announce Type: new Abstract: LLM serving systems store, offload, and share KV caches, exposing token-level representations to infrastructure operators and co-tenants. Shuffled obfuscation combines secret linear transforms with fresh permutations, claiming security from b! possible shufflings. We show that input symmetry invalidates this counting argument: security depends on distinguishable outputs under chosen inputs. Repeated tokens produce identical first-layer Value rows, making every row permutation leave the data unchanged. Only auxiliary structures such as a single-row recovery marker vary, reducing the effective state space from b! to b. We construct Repeat-to-Reveal. The attacker collects the b distinguishable states from its own probes and exploits their rank-one differences to recover an equivalent denoiser without knowing the defender's secret parameters. A one-time calibration transfers across requests sharing the same secret epoch, enabling passive token-multiset recovery from subsequently observed cache blocks through public-model dictionary matching. We instantiate the attack on official KV-Cloak and evaluate 3,000 real WildChat user prompts across nine models and eleven configurations. The attack recovers the secret parameters with high accuracy and achieves 100 percent token-multiset recovery on GPU. Refreshing row-level secrets between epochs interrupts cross-request transfer, confirming secret reuse scope as the operative vulnerability. We further confirm orbit collapse on two other open-source defenses: the sequence-permutation implementation of Thomas et al. and PermLLM. The KV-Cloak developers invited a detailed report through their private vulnerability reporting channel.
Source:https://arxiv.org/abs/2611.24276PreviousRetained Encrypted Search with Certified Split JoinsNextAutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents
Related posts
VOS: Variate Ordering Strategies for Skyline Query Optimization
0arXiv cs.DB
MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selection
0arXiv cs.DB
Exploring Agentic Visual Analytics: A Co-Evolutionary Framework of Roles and Workflows
0arXiv cs.DB
ProvCards: Artifact-Oriented Provenance for Heterogeneous Scientific Workflows
0arXiv cs.DB
Towards Online Adaptive LLM-based Semantic Filtering
0arXiv cs.DB
Cascadeability and the Realization Gap: An Empirical Study of LLM-Powered Semantic Filtering
0arXiv cs.DB