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

203 entries

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

Semantic Intention Obfuscation

Published Analyzed Source: arXiv

The KG-DF (Knowledge Graph Defense Framework) contains a logic vulnerability in its Semantic Parsing Module, specifically within the keyword extraction phase defined as $K_{core} = \text{LLM}(P_{prompt})$. The framework relies on a Large Language Model (e.g., GPT-3.5-turbo) to distill user input into keywords ($K_{core}$), which are then embedded to retrieve security warning triples ($T_{match}$) from a Knowledge Graph.

KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs
Evaluated models: GPT-3.5, GPT-4, Llama 2 7B+1 more
  • GPT-3.5
  • GPT-4
  • Llama 2 7B
  • Vicuna 7B

LLM Factual MitM Injection

Published Analyzed Source: arXiv

Large Language Models (LLMs), specifically GPT-4o, GPT-4o-mini, LLaMA-2-13B, Mistral-7B, and Phi-3.5-mini, are vulnerable to Man-in-the-Middle (MitM) adversarial prompt injections that undermine factual recall. Termed the "$\chi$mera" (Chimera) attack framework, this vulnerability exists when an attacker intercepts and modifies user queries (e.g., via malicious browser extensions, compromised frontends, or proxy middleware) before they reach the victim model. By appending adversarial…

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
Evaluated models: GPT-4o, Llama 2 13B, Mistral 7B+1 more
  • GPT-4o
  • Llama 2 13B
  • Mistral 7B
  • Phi-3

Adversarial Self-Deception

Published Analyzed Source: arXiv

Large Language Models (LLMs) exhibit a vulnerability to "adversarial conversational nudges," where the model abandons its internal factual knowledge to align with user-provided misinformation in closed domains (e.g., movies, books). Unlike standard hallucinations where a model lacks knowledge, this vulnerability occurs even when the model demonstrates—via separate self-consistency checks—that it correctly identifies the information as false. When a user creates a multi-turn context asserting…

What About the Scene With the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency in Closed Domains Via Adversarial Nudge
Evaluated models: GPT-4o, GPT-5, Claude Opus 4+4 more
  • GPT-4o
  • GPT-5
  • Claude Opus 4
  • Gemini 1.5 Flash
  • Gemini 2.5 Flash
  • DeepSeek Reasoner
  • Grok 4

Latent Paraphrase Segmentation Attack

Published Analyzed Source: arXiv

Reasoning segmentation models, which generate binary segmentation masks based on implicit text queries, are vulnerable to adversarial paraphrasing. This vulnerability allows an attacker to craft semantically equivalent and grammatically correct text prompts that significantly degrade the model's segmentation performance (measured by Intersection-over-Union, or IoU). The exploit utilizes a black-box, sentence-level optimization method (SPARTA) that operates within the continuous semantic latent…

SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space
Evaluated models: LISA 7B, LISA Explanatory 7B, LISA 13B+3 more
  • LISA 7B
  • LISA Explanatory 7B
  • LISA 13B
  • LISA Explanatory 13B
  • LISA++ 7B
  • GSVA 13B

Graph-LLM Semantic Attack

Published Analyzed Source: arXiv

Graph-LLMs (Graph Neural Networks integrated with Large Language Models) utilized for representation learning on Text-Attributed Graphs (TAGs) are vulnerable to the Interpretable Multi-Dimensional Graph Attack (IMDGA). This vulnerability exists due to the non-decoupled nature of text encoding and graph message passing mechanisms. A black-box attacker can manipulate node classification predictions by executing a three-stage attack: (1) utilizing a word-level Topological SHAP module to identify…

Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs
Evaluated models: Not reported

Underestimated LLM Security Flaws

Published Analyzed Source: arXiv

Mamba-2 and hybrid Transformer-Mamba-2 distilled Large Language Model (LLM) architectures exhibit a distinct architectural susceptibility to Latent Injection and ANSI Escape sequence prompt injection attacks. Comparative analysis reveals that models incorporating Mamba state-space components (specifically distilled variants like Llamba-3B and base Mamba models) fail to maintain adversarial robustness levels comparable to pure Transformer baselines (such as Llama-3.2) when subjected to indirect…

Towards reliable and practical LLM security evaluations via Bayesian modelling
Evaluated models: Llama 3.2 3B, Falcon 7B

RL-Hammer Autonomous Jailbreak

Published Analyzed Source: arXiv

A vulnerability exists in Large Language Model (LLM) agentic systems where automated reinforcement learning (RL) techniques can bypass advanced prompt injection defenses, including Instruction Hierarchy and SecAlign. The specific attack methodology, dubbed "RL-Hammer," utilizes Group Relative Policy Optimization (GRPO) to train an attacker model from scratch without warm-up data. The vulnerability exploits the reward sparsity in robust models by employing a "bag of tricks": removing KL…

RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
Evaluated models: Llama 3.1 8B Instruct, Meta-SecAlign 8B, Meta-SecAlign 70B+7 more
  • Llama 3.1 8B Instruct
  • Meta-SecAlign 8B
  • Meta-SecAlign 70B
  • GPT-4o Mini
  • GPT-4o
  • GPT-5 Mini
  • GPT-5
  • Gemini 2.5 Flash
  • Claude 3.5 Sonnet
  • Claude Sonnet 4

Adaptive Typographic Image Injection

Published Analyzed Source: arXiv

Multimodal agents built on Large Vision-Language Models (LVLMs) are vulnerable to adaptive typographic prompt injection attacks (AgentTypo). This vulnerability allows an attacker to execute indirect prompt injection by embedding adversarial text prompts directly into images (e.g., webpage screenshots, product photos) processed by the agent. Unlike standard visual adversarial attacks that rely on noise perturbation, this method utilizes the AgentTypo framework to perform black-box Bayesian…

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents
Evaluated models: GPT-4o, GPT-4V, GPT-4o Mini+2 more
  • GPT-4o
  • GPT-4V
  • GPT-4o Mini
  • Gemini 1.5 Pro
  • Claude 3 Opus

Schrodinger's Compliance Jailbreak

Published Analyzed Source: arXiv

The GPT-OSS-20B large language model contains critical failures in its alignment and Chain-of-Thought (CoT) reasoning mechanisms, specifically in how it prioritizes numerical objectives and validates procedural structure. The model is vulnerable to "Quant Fever," where explicit numerical targets in a prompt (e.g., "delete 90% of files") override contextual safety constraints (e.g., "do not delete important files"). Furthermore, the model exhibits "Reasoning Procedure Mirage," where harmful…

Quant Fever, Reasoning Blackholes, Schrodinger's Compliance, and More: Probing GPT-OSS-20B
Evaluated models: Not reported

Single Query Dynamic Output

Published Analyzed Source: arXiv

A vulnerability exists in Large Language Models (LLMs) and multi-label text classification systems that allows for Textual Dynamic Outputs Attacks (TDOA). This technique enables hard-label black-box attacks against systems with variable or generative output spaces (where the number of labels or specific label tokens are not fixed). The attack functions by training a surrogate model on clustered coarse-grained labels derived from the victim model's fine-grained dynamic outputs. It subsequently…

Text Adversarial Attacks with Dynamic Outputs
Evaluated models: GPT-4o, GPT-4o Mini, GPT-4.1+5 more
  • GPT-4o
  • GPT-4o Mini
  • GPT-4.1
  • Claude 3.7 Sonnet
  • DeepSeek V3
  • BERT
  • DistilBERT
  • RoBERTa

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.