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

337 entries

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

Unified Robustness Gap

Published Analyzed Source: arXiv

Text scoring models, including dense retrievers, rerankers, and reward models, are vulnerable to score manipulation attacks via search-based discrete perturbations and content injection. An attacker can systematically modify candidate texts using rudimentary string manipulations, gradient-guided token swaps (e.g., HotFlip), masked language modeling (MLM) swaps, or query/sentence injections to spuriously increase model scores. This structural failure condition allows an irrelevant passage or a…

Unifying Adversarial Robustness and Training Across Text Scoring Models
Evaluated models: E5 BERT-base, Qwen 3 0.6B, Llama 3.2 3B Instruct+2 more
  • E5 BERT-base
  • Qwen 3 0.6B
  • Llama 3.2 3B Instruct
  • Llama 3.1 8B Instruct
  • Skywork Reward V2

Payment Protocol Whisper Attack

Published Analyzed Source: arXiv

The Google Agent Payments Protocol (AP2), specifically within the reference implementation built using the Google Agent Development Kit (ADK) and Gemini models, contains vulnerabilities allowing for both indirect and direct prompt injection. The architecture fails to sufficiently isolate the Large Language Model (LLM) context from untrusted external data sources and user inputs.

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection
Evaluated models: Gemini 2.5 Flash

Query-Agnostic Retrieval Poisoning

Published Analyzed Source: arXiv

A vulnerability in Large Language Model-based Retrieval (LLMR) systems allows attackers to intentionally hide specific documents from being retrieved (e.g., in RAG pipelines or search engines) by appending a small number of adversarially crafted, query-agnostic tokens. The attack operates in a complete black-box setting: it requires no knowledge of the victim's queries, the target retrieval model's parameters, or the underlying document corpus. By utilizing Document-Query Adversarial (DQ-A)…

" Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
Evaluated models: Mistral 7B, Qwen 2.5 7B

Semantic Cache Collision Hijack

Published Analyzed Source: arXiv

Semantic caching mechanisms in LLM applications are vulnerable to cross-tenant cache key collision attacks (CacheAttack) due to the inherent mathematical conflict between locality-preserving fuzzy hashing and cryptographic collision resistance (the avalanche effect). An attacker can leverage gradient-based search algorithms to optimize an adversarial discrete suffix that, when appended to a malicious prompt, forces its output embedding vector to collide with the embedding of a targeted benign…

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
Evaluated models: Llama 3.1 8B, Mistral 7B, DeepSeek R1

LLM Grading Compliance Paradox

Published Analyzed Source: arXiv

Large Language Models (LLMs) employed as automated code evaluators ("Universal Graders") are vulnerable to Semantic-Instruction Decoupling, a form of adversarial prompt injection that exploits the "Syntax-Semantics Gap." Attackers can embed adversarial directives into syntactically inert regions of the Abstract Syntax Tree (AST)—specifically comments, docstrings, variable names, and whitespace. While these regions are discarded by compilers (trivia nodes) or treated as arbitrary symbols…

The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation
Evaluated models: GPT-5, Llama 3.1 8B, DeepSeek V3

LLM Router Rerouting

Published Analyzed Source: arXiv

LLM routing systems are vulnerable to adversarial rerouting attacks where malicious triggers prepended to user queries manipulate the router's model-selection mechanism. Because LLM routers function as classifiers evaluating query complexity to balance computational cost and response quality, an attacker can craft adversarial prefixes that distort the query's latent semantic representation. This exploits the router's decision boundaries, forcing the system to misclassify the input and redirect…

RerouteGuard: Understanding and Mitigating Adversarial Risks for LLM Routing
Evaluated models: GPT-4, GPT-4o, GPT-5+2 more
  • GPT-4
  • GPT-4o
  • GPT-5
  • Llama 3 8B
  • Mixtral 8x7B

Agent Over-Trigger Containment

Published Analyzed Source: arXiv

Autonomous Incident Response (IR) and Security Operations Center (SOC) agents utilizing frontier LLMs are vulnerable to adversarial over-triggering via contextualized prompt injections. When processing untrusted artifacts (such as SQLite logs, alerts, or phishing emails) in a dual-control environment, these agents exhibit a severe calibration failure: they lack action restraint and execute disruptive containment tools prematurely. Attackers can exploit this by embedding T2 (contextualized…

OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence
Evaluated models: GPT-5.2, Claude Sonnet 4.5, DeepSeek V3.2+1 more
  • GPT-5.2
  • Claude Sonnet 4.5
  • DeepSeek V3.2
  • Qwen 3 4B Instruct

Hard-Negative Prompt Evasion

Published Analyzed Source: arXiv

Embedding-based LLM prompt injection detectors, specifically those based on the DeBERTa-v3 architecture, are vulnerable to adversarial evasion attacks utilizing "hard-negative" mining and fuzzing techniques. Attackers can circumvent detection mechanisms by iteratively generating adversarial prompts that are semantically malicious but structurally mutated to evade the classifier's decision boundary. Specific evasion vectors identified include semantic fuzzing (paraphrasing), syntactic fuzzing…

Proactive Hardening of LLM Defenses with HASTE
Evaluated models: GPT-4o

LLM Agent Disguised URL Bypass

Published Analyzed Source: arXiv

Large Language Models (LLMs) acting as web agents exhibit a vulnerability in their decision-making process when validating external URLs. The models fail to correctly identify malicious domains when the Uniform Resource Locator (URL) structure—specifically the subdomain, directory path, or query parameters—is manipulated to include semantically "safe" keywords or mimic benign websites (URL disguising). Attackers can induce the agent to accept and visit a malicious link by embedding natural…

MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs
Evaluated models: GPT-3.5, GPT-4o, Llama 2 7B+4 more
  • GPT-3.5
  • GPT-4o
  • Llama 2 7B
  • Llama 3 8B
  • Mistral 7B
  • DeepSeek V3
  • Mixtral 8x7B

MCP Server-Side Injection

Published Analyzed Source: arXiv

The Model Context Protocol (MCP) specification v1.0 contains fundamental architectural vulnerabilities enabling server-side prompt injection and privilege escalation. The protocol relies on bidirectional sampling (sampling/createMessage) without cryptographic origin authentication or UI distinction, allowing connected servers to inject content that the LLM backend interprets as legitimate user input. Additionally, the protocol lacks isolation boundaries between concurrent server connections…

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
Evaluated models: GPT-4o, Claude 3.5 Sonnet, Llama 3.1 70B

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.