AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching

Zhixiang Zhang, Zesen Liu, Yuchong Xie, Quanfeng Huang, Dongdong She

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: LLM jailbreak and injection defense · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use GCG-based suffix generator with validator instead of genetic algorithm generator (ablation)CacheAttack · semantic cache response hijackingHit Rate (%): 36.2 -> 86.9Improved
use surrogate-assisted validation (CacheAttack-2) instead of direct target validation (CacheAttack-1) (ablation)CacheAttack · semantic cache response hijackingHit Rate (%): 86.9 -> 83.1Mixed
use surrogate embedding model different from targetCacheAttack-2 · cross-model transfer (MiniLM surrogate to BGE target)Hit Rate (%): 93.4 (in-model) -> 49.8Hurt
use surrogate with similar architecture to target (E5 to BGE)CacheAttack-2 · cross-model transferHit Rate (%): 49.8 (MiniLM to BGE) vs 81.7 (E5 to BGE)Improved
add key salting (prefix) to cache keyssemantic cache · response hijackingHit Rate reduction (pp): 19.2 pp HR reduction, 25.4 pp ISR reductionMixed
add suffix salting to cache keyssemantic cache · response hijackingHit Rate reduction (pp): 9.5 pp HR reduction, 10.2 pp ISR reductionNo clear effect
add perplexity term to the suffix objective and perplexity screening at insertionCacheAttack generator / cache defense · semantic cachestealthNo clear effect
add per-user cache isolationsemantic cache · multi-tenant cachingcross-user hijacking and hit rateMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy