# LaCache: Robust Semantic Caching for LLM Serving

arXiv: https://arxiv.org/abs/2608.01718 · HTML: https://mlsanity.com/paper/2608.01718/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 24 of 24)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://mlsanity.com/paper/2411.02397/) (2024)
- [RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.12457/) (2024)
- [ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition](https://mlsanity.com/paper/2402.15220/) (2024)
- [Hydragen: High-Throughput LLM Inference with Shared Prefixes](https://mlsanity.com/paper/2402.05099/) (2024)
- [KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider](https://mlsanity.com/paper/2506.02634/) (2025)
- [Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling](https://mlsanity.com/paper/2403.01251/) (2024)
- [Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.15734/) (2025)
- [Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information](https://mlsanity.com/paper/2311.11509/) (2023)
- [BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching](https://mlsanity.com/paper/2412.03594/) (2024)
- [The Early Bird Catches the Leak: Unveiling Timing Side Channels in LLM Serving Systems](https://mlsanity.com/paper/2409.20002/) (2024)
- [GraphRAG under Fire](https://mlsanity.com/paper/2501.14050/) (2025)
- [GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching](https://mlsanity.com/paper/2411.05276/) (2024)
- [Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference](https://mlsanity.com/paper/2508.09442/) (2025)
- [Auditing Prompt Caching in Language Model APIs](https://mlsanity.com/paper/2502.07776/) (2025)
- [vCache: Verified Semantic Prompt Caching](https://mlsanity.com/paper/2502.03771/) (2025)
- [SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching](https://mlsanity.com/paper/2504.00970/) (2025)
- [SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching](https://mlsanity.com/paper/2509.24832/) (2025)
- [From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching](https://mlsanity.com/paper/2601.23088/) (2026)

## Built on by (most cited first, 1 of 1)

- [Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning](https://mlsanity.com/paper/2609.35908/) (2026)

## Abstract (arXiv)

Semantic caching, reusing responses to answer semantically similar queries, has seen growing adoption in LLM serving, offering faster responses and reduced costs. Yet existing schemes are fundamentally vulnerable to cache-collision attacks, wherein an adversary pollutes the cache by injecting adversarial queries, corrupting responses to subsequent legitimate requests. We present LaCache, a simple yet principled redesign of semantic caching that provides provable defense against such attacks. The key insight is that while the adversary has full control over the adversarial query, it has far less control over the corresponding LLM-generated response, which must simultaneously satisfy multiple competing constraints. Thus, LaCache shifts the integrity check from the query to the response: rather than checking only the cache hit of a query, LaCache additionally checks the cache hit of its first k speculatively decoded tokens. Analytically, we prove that LaCache detects any cache-collision attack that produces a semantically distinct response with provably high probability. Empirically, evaluation across diverse LLMs and benchmarks confirms that LaCache reduces attack hit rate to near zero while preserving over 90% of benign cache utility. To our best knowledge, this work is the first to exploit the inherent constraints on adversarial responses in cache-collision attacks to provide provable security, pointing to a promising direction for building robust semantic caching.