Updated 7/21/2026

Language Model Security Database

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

959 research findings · 1077 evaluated models

Findings

959

Models evaluated

1077

Paper-evaluated models

Any selected model can match.

Refine by category

Findings match every selected category.

Attack Type

Attack Context

Architecture Components1 selected

Attack Surface1 selected

Impact

Advanced filters

Published fromPublished throughSource or venue

arXiv is the only currently indexed source.

Evidence status

Filtered research findings

2 entries

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

Evaluator Consensus Manipulation

Updated 2/22/2026

A vulnerability exists in the "Adaptive Trust Weighting" mechanism of the Cost-Aware Proof of Quality (PoQ) protocol for decentralized LLM inference. The protocol updates evaluator trust weights based on the deviation of a submitted score from the consensus score of the current round. Because the consensus score is derived from the very scores being evaluated (a self-referential feedback loop), the mechanism fails to distinguish between honest and coordinated malicious evaluators…

Adaptive and Robust Cost-Aware Proof of Quality for Decentralized LLM Inference Networks

Source: arXiv

Confounder Gadgets Reroute LLMs

Updated 1/14/2026

A vulnerability exists in Large Language Model (LLM) routing systems (control planes) that allows for the manipulation of inference flow via adversarial input sequences. LLM routers, which dynamically direct user queries to either "weak" (cheaper) or "strong" (expensive) models based on predicted query complexity, can be bypassed by appending specific, pre-optimized token sequences known as "confounder gadgets." These gadgets artificially inflate the router's complexity score for an input…

Rerouting llm routers

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.