Last analyzed 9/9/2026

Language Model Security Database

Explore primary-source AI security research, evaluated models, attack techniques, and defensive evidence.

985 research findings · 1123 evaluated models

Findings

985

Models evaluated

1123

Paper-evaluated models

Any selected model can match.

Refine by category

Findings match every selected category.

Attack Type1 selected

Attack Context

Architecture Components1 selected

Attack Surface1 selected

Impact

Advanced filters

Published fromPublished through

Research indexed from arXiv.

Evidence status

Filtered research findings

2 entries

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

Document reconstruction from exposed retrieval embeddings

Published 9/4/2026

Analyzed 9/9/2026

Exposed retrieval embeddings can reveal source text. SHAQ evaluates indexing generated queries instead of direct document embeddings to reduce that leakage.

Shadow Queries for Private Retrieval in Vector Databases

Evaluated models: QwQ 32B

Source: arXiv

RAG Knowledgebase Exfiltration

Published 2/1/2026

Analyzed 2/21/2026

Retrieval-Augmented Generation (RAG) systems are vulnerable to iterative knowledge-extraction attacks designed to reconstruct the underlying private knowledge base. The vulnerability exists due to the decoupled optimization of the retrieval and generation phases. Attackers can craft adversarial queries consisting of two distinct components: an "Information" component (optimized via gradient descent or random sampling to steer embeddings toward specific, diverse regions of the vector space) and…

Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation

Evaluated models: GPT-4o, Llama 3 8B, Qwen 2.5 7B

Source: arXiv

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.