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.

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

Untargeted Gradient Jailbreak

Published Analyzed Source: arXiv

A vulnerability exists in certain safety-aligned Large Language Models (LLMs) due to an untargeted, gradient-based optimization attack method called Untargeted Jailbreak Attack (UJA). Unlike previous targeted attacks (e.g., GCG) that optimize a prompt to elicit a predefined string (e.g., "Sure, here is..."), UJA optimizes for a general objective: maximizing the unsafety probability of the model's response, as quantified by an external judge model.

Untargeted Jailbreak Attack
Evaluated models: DeepSeek R1, GPT-2 Large, GPT-4+11 more
  • DeepSeek R1
  • GPT-2 Large
  • GPT-4
  • GPT-4o
  • Llama 2 13B
  • Llama 3 70B Instruct
  • Llama 3 8B Instruct
  • Llama 3.1 8B Instruct
  • Llama Guard 3
  • Mistral 7B Instruct v0.3
  • Qwen 2.5 7B Instruct
  • Qwen 3 8B Instruct
  • RoBERTa
  • Vicuna 7B v1.5

Controlled-Release Guard Bypass

Published Analyzed Source: arXiv

A vulnerability termed "Controlled-Release Prompting" allows attackers to bypass lightweight input filters (prompt guards) deployed in front of Large Language Models (LLMs). The attack exploits the computational resource asymmetry between the resource-constrained guard model and the highly capable target model. Attackers encode malicious instructions using obfuscation techniques—such as substitution ciphers (Timed-Release) or verbose character descriptions (Spaced-Release)—that require…

Bypassing Prompt Guards in Production with Controlled-Release Prompting
Evaluated models: Gemini 2.5 Flash, Gemini 2.5 Pro, DeepSeek R1+2 more
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • DeepSeek R1
  • Grok 3
  • GPT-5 Mini

LLM Self-Targeted Jailbreak

Published Analyzed Source: arXiv

A security vulnerability exists in the safety alignment mechanisms of Large Language Models (LLMs), specifically susceptible to the "Dynamic Target Attack" (DTA). Unlike traditional gradient-based jailbreaks (e.g., GCG) that optimize adversarial suffixes toward a fixed, low-probability static target (e.g., "Sure, here is..."), DTA exploits the model's own output distribution. The attack iteratively samples candidate responses from the target model using relaxed decoding parameters (high…

Dynamic Target Attack
Evaluated models: Llama 3 8B, Llama 3.2 1B, Mistral 7B+3 more
  • Llama 3 8B
  • Llama 3.2 1B
  • Mistral 7B
  • Qwen 2.5 7B
  • Gemma 7B
  • Vicuna 7B

Code Agent Executable Jailbreaks

Published Analyzed Source: arXiv

AI code agents are vulnerable to jailbreaking attacks that cause them to generate or complete malicious code. The vulnerability is significantly amplified when a base Large Language Model (LLM) is integrated into an agentic framework that uses multi-step planning and tool-use. Initial safety refusals by the LLM are frequently overturned during subsequent planning or self-correction steps within the agent's reasoning loop.

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
Evaluated models: Claude 3.7 Sonnet, DeepSeek R1, Dolphin Mistral 24B Venice+6 more
  • Claude 3.7 Sonnet
  • DeepSeek R1
  • Dolphin Mistral 24B Venice
  • GPT-4.1
  • Llama 3 8B
  • Llama 3.1 70B
  • Mistral Large 2.1
  • o1
  • Qwen 3 235B-A22B

Intermediate Denoising Priming

Published Analyzed Source: arXiv

A "Priming Vulnerability" exists in Masked Diffusion Language Models (MDLMs) due to their iterative, parallel denoising inference mechanism. Unlike autoregressive models that generate tokens sequentially, MDLMs refine a sequence from a fully masked state through multiple denoising steps. The vulnerability arises because standard safety alignment (e.g., SFT, DPO, MOSA) typically optimizes the model to generate safe responses only when initialized from a fully masked sequence. If an affirmative…

Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
Evaluated models: Not reported

Self-Amplifying Memory Poisoning

Published Analyzed Source: arXiv

Large Language Model (LLM) agents utilizing long-term memory or Retrieval-Augmented Generation (RAG) are vulnerable to context-dependent memory injection attacks. Unlike traditional prompt injections that are overtly malicious, this vulnerability involves injecting records that appear benign and coherent in isolation—thereby bypassing standard perplexity filters and static content moderation (e.g., LlamaGuard). These records contain "sleeping" malicious logic that is only activated when…

A-memguard: A proactive defense framework for llm-based agent memory
Evaluated models: GPT-4o, Llama 3.1 8B

RL-driven Formalized Prompt Jailbreaking

Published Analyzed Source: arXiv

A vulnerability exists in aligned Large Language Models (LLMs) where a harmful instruction can be obfuscated through a multi-step formalization process, bypassing safety mechanisms. The attack, named Prompt Jailbreaking via Semantic and Structural Formalization (PASS), uses a Reinforcement Learning (RL) agent to dynamically construct an adversarial prompt. The agent learns to apply a sequence of actions—such as symbolic abstraction, logical encoding, mathematical representation, metaphorical…

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
Evaluated models: DeepSeek V3, Qwen 3 14B

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

Search Agents Vulnerable to Unreliable Results

Published Analyzed Source: arXiv

LLM-based search agents are vulnerable to manipulation via unreliable search results. An attacker can craft a website containing malicious content (e.g., misinformation, harmful instructions, or indirect prompt injections) that is indexed by search engines. When an agent retrieves and processes this page in response to a benign user query, it may uncritically accept the malicious content as factual and incorporate it into its final response. This allows the agent to be used as a vector for…

SafeSearch: Automated Red-Teaming for the Safety of LLM-Based Search Agents
Evaluated models: DeepSeek R1, Gemini 2.5 Flash, Gemini 2.5 Pro+11 more
  • DeepSeek R1
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • Gemma 3 27B IT
  • GPT-4.1
  • GPT-4.1 Mini
  • GPT-5
  • GPT-5 Mini
  • GPT-oss 120B
  • Kimi K2
  • o4-mini
  • Qwen 3 235B-A22B
  • Qwen 3 32B
  • Qwen 3 8B

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.