Skip to main content
LLM Security Database
Skip to research search
Last analyzed Sep 9, 2026

Language Model Security Database

985 research findings · 1119 evaluated models

Filtered research findings

3 entries

Matches every word across titles, descriptions, sources, affected systems, and models.

Agent Lifecycle Compound Threats

Published Analyzed Source: arXiv

OpenClaw is vulnerable to persistent memory poisoning, allowing an attacker to manipulate the agent's long-term memory store (MEMORY.md) via prompt injection. Because the autonomous agent continuously integrates this memory file as context for all subsequent reasoning and task planning, injected payloads act as durable behavioral constraints. This allows an attacker to persistently alter the agent's core policy, manipulate tool selection, and hijack future sessions without any further…

Taming openclaw: Security analysis and mitigation of autonomous llm agent threats
Evaluated models: Not reported
Application layer
Infrastructure
Prompt layer
Injection

LLM Prefix Cache Reconstruction

Published Analyzed Source: arXiv

Automatic Prefix Caching (APC) in multi-tenant LLM serving systems introduces a timing side-channel vulnerability that permits cross-tenant data leakage. APC shares computed Key-Value (KV) tensors across different users when their requests share identical initial tokens. Because reusing cached tensors is significantly faster than recomputing them, a measurable difference in Time-To-First-Token (TTFT) exists between cache hits and misses. An attacker can exploit this shared cache by sending…

PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems
Evaluated models: Gemma 3 4B IT, Llama 2 7B Chat, Llama 2 13B Chat+6 more
  • Gemma 3 4B IT
  • Llama 2 7B Chat
  • Llama 2 13B Chat
  • LLaVA OneVision Qwen2 0.5B
  • LLaVA OneVision Qwen2 7B Chat
  • Qwen2-VL 2B Instruct
  • Qwen2-VL 7B Instruct
  • Qwen 2.5 VL 3B Instruct
  • Qwen 2.5 VL 7B Instruct
Infrastructure
Extraction
Side channel
Black-box

KV-Cache Sharing Timing Side-channel

Published Analyzed Source: arXiv

Multi-tenant Large Language Model (LLM) inference systems utilizing global Key-Value (KV) cache sharing are vulnerable to a timing side-channel attack. By measuring the Time-To-First-Token (TTFT) latency of crafted API requests, an unprivileged remote attacker can determine if specific token sequences have been previously processed and cached by the system for other users. This observable timing difference between cache hits (low TTFT) and cache misses (high TTFT) allows for the token-by-token…

Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
Evaluated models: Phi-4 14B, Qwen 3 30B-A3B, Qwen 3 32B+3 more
  • Phi-4 14B
  • Qwen 3 30B-A3B
  • Qwen 3 32B
  • Llama 3.3 70B Instruct
  • Qwen 3 235B-A22B
  • DeepSeek R1
Infrastructure
Side channel
Extraction
Black-box

Research methodology

Entries summarize publicly available primary-source security research. Model names reflect only systems explicitly evaluated by the cited paper, and measurements are research-reported unless independent verification is stated.

Discovery and publication are separate: new papers enter a candidate queue, then require human review and explicit approval before publication. Updates follow that review process, not a guaranteed daily publishing schedule. “Last analyzed” is the newest analysis date among published entries; it does not mean that all recent research has been covered.