HijackKV: New Threat in Position-Independent KV Cache Reuse
Quick summary
arXiv:2607.19957v2 Announce Type: replace-cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs). Traditional prefix-based reuse has low cache hit rates across inference requests because it requires exact token and position matches. To improve efficiency, recent system optimizations introduce position-independent KV reuse, allowing KV cache to be reused whenever identical text chunks appear, regardless of their position in the sequence. We show this design introduces a new threat, KV Cache Hijacking. Since KV caches are retrieved by token match but encod
Key takeaways
- arXiv:2607.19957v2 Announce Type: replace-cross Abstract: Key-Value (KV) cache reduces inference latency in large language models (LLMs).
- Traditional prefix-based reuse has low cache hit rates across inference requests because it requires exact token and position matches.
- To improve efficiency, recent system optimizations introduce position-independent KV reuse, allowing KV cache to be reused whenever identical text chunks appear, regardless of their position in the sequence.
Why it matters
The importance of “HijackKV: New Threat in Position-Independent KV Cache Reuse” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments