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

610 entries

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

Persistent Agent Context Injection

Published Analyzed Source: arXiv

Conventional LLM agent architectures suffer from a working memory contamination vulnerability due to indiscriminate memory accumulation. When these agents retrieve external data via tools (e.g., web search, reading emails), the entire raw output is appended directly to their continuous context window. If the external data contains an Indirect Prompt Injection (IPI) payload, the malicious instruction persists in the agent's working memory across its entire multi-step reasoning workflow. This…

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
Evaluated models: GPT-4o Mini, GPT-4o, GPT-5.1+3 more
  • GPT-4o Mini
  • GPT-4o
  • GPT-5.1
  • Claude 3.7 Sonnet
  • Gemini 2.5 Pro
  • Qwen 2.5 7B Instruct

Clinical Prompt Injection Harm

Published Analyzed Source: arXiv

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems deployed in clinical workflows are vulnerable to direct and indirect (RAG-mediated) medical prompt injection attacks. Attackers can embed malicious instructions within user queries or external retrieved documents (such as poisoned clinical guidelines or PDFs). By exploiting "authority framing" (e.g., formatting the payload as a clinical guideline update or an editor's note), the injections successfully bypass generic…

MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs
Evaluated models: Qwen 2.5 7B Instruct, Qwen 2.5 32B Instruct, Qwen 2.5 72B Instruct+10 more
  • Qwen 2.5 7B Instruct
  • Qwen 2.5 32B Instruct
  • Qwen 2.5 72B Instruct
  • Llama 3.1 8B Instruct
  • Llama 3.1 70B Instruct
  • Mixtral 8x7B
  • Mixtral 8x22B v0.1
  • MedGemma 4B
  • MedGemma 27B
  • Meditron 7B
  • Meditron 70B
  • BioMistral 7B
  • MMed-Llama 3 8B

History Reweighting Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs), specifically LLaMA-3.2-11B, Qwen3-14B, Gemma 3-12B, and GPT-oss-20B, are vulnerable to black-box jailbreaking attacks via history-guided reinforcement learning (RL). The vulnerability arises from the models' inability to detect adversarial intent when prompts are iteratively refined based on historical interaction signals. An attacker can exploit this by employing a History-augmented Reinforcement Learning (HRL) framework, such as "TrailBlazer," which augments the…

TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking
Evaluated models: GPT-oss 20B, Llama 3.2 11B, Qwen 3 14B+1 more
  • GPT-oss 20B
  • Llama 3.2 11B
  • Qwen 3 14B
  • Gemma 3 12B

Covert Template System Backdoor

Published Analyzed Source: arXiv

A vulnerability exists in the chat template mechanism used by Large Language Model (LLM) tokenizers, specifically within the Jinja2 templating engine commonly employed by libraries such as Hugging Face Transformers. By modifying the chat_template field within the tokenizer configuration (e.g., tokenizer_config.json), an attacker can inject hidden backdoor instructions into the system prompt. These instructions are concatenated with legitimate user inputs during the tokenization process…

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models
Evaluated models: Llama 3.1 8B Instruct, DeepSeek LLM 7B Chat, Llama 3.1 70B Instruct+6 more
  • Llama 3.1 8B Instruct
  • DeepSeek LLM 7B Chat
  • Llama 3.1 70B Instruct
  • Yi 1.5 Chat 34B
  • Mistral Small Instruct 2409
  • Phi-3.5 Mini Instruct
  • DeepSeek V3.2 Exp
  • Gemini 2.5 Flash
  • GPT-4o Mini

Evolutionary Hidden Knowledge Recovery

Published Analyzed Source: arXiv

Large Language Models (LLMs) subjected to machine unlearning techniques (specifically AltPO, GradDiff, IDKDPO, IDKNLL, UNDIAL, NPO, and SimNPO) contain a vulnerability regarding the persistence of latent knowledge. Despite achieving high "forgetting" scores on standard, benign benchmarks, these models remain susceptible to black-box evolutionary adversarial attacks. An attacker can utilize an automated framework (REBEL) comprising a "Hacker" model and a "Judge" model to iteratively mutate…

REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop
Evaluated models: Not reported

Invisible Prompt Phishing Evasion

Published Analyzed Source: arXiv

Multimodal LLM-based phishing detection systems are vulnerable to indirect prompt injection via "perceptual asymmetry." Attackers can embed hidden instructions within a phishing site's HTML, CSS, URLs, or rendered images that remain imperceptible to human victims but are parsed and executed by the evaluating LLM. This vulnerability allows threat actors to manipulate the LLM's contextual understanding, forcing it to misclassify malicious sites as benign (Legitimate Pretexting), trigger safety…

Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing Detection
Evaluated models: GPT-5, Grok 4 Fast Non-Reasoning, Llama 4 Maverick+1 more
  • GPT-5
  • Grok 4 Fast Non-Reasoning
  • Llama 4 Maverick
  • Gemma 3 27B

Learned Universal Prompt Injection

Published Analyzed Source: arXiv

Large Language Model (LLM) agents are vulnerable to automated prompt injection attacks generated via Reinforcement Learning (RL). The attack methodology, termed "AutoInject," utilizes Group Relative Policy Optimization (GRPO) combined with a comparison-based feedback mechanism to generate universal adversarial suffixes. Unlike traditional jailbreaks that optimize for generic affirmative responses (e.g., "Sure"), this vulnerability allows an attacker to optimize for specific, parameterized tool…

Learning to Inject: Automated Prompt Injection via Reinforcement Learning
Evaluated models: Gemini 2.5 Flash, Gemini 2.0 Flash, GPT-4.1 Nano+6 more
  • Gemini 2.5 Flash
  • Gemini 2.0 Flash
  • GPT-4.1 Nano
  • GPT-5 Nano
  • GPT-4o Mini
  • Claude 3.5 Sonnet
  • Meta-SecAlign 70B
  • Qwen 3 4B
  • Gemma 3 4B

Visual Exclusivity Agentic Jailbreak

Published Analyzed Source: arXiv

Frontier Multimodal Large Language Models (MLLMs) are vulnerable to Visual Exclusivity (VE) attacks, an "Image-as-Basis" threat where malicious intent is achieved through joint reasoning over benign text and complex technical visual content (e.g., blueprints, schematics, network diagrams). Unlike wrapper-based attacks that conceal malicious text via typography or adversarial noise, VE exploits the model's core visual reasoning capabilities. Attackers can bypass safety filters by combining…

Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
Evaluated models: Llama 3.2 11B Vision, InternVL3 8B, Qwen3-VL 8B+5 more
  • Llama 3.2 11B Vision
  • InternVL3 8B
  • Qwen3-VL 8B
  • GPT-4o
  • GPT-5
  • Claude 3.7 Sonnet
  • Claude Sonnet 4.5
  • Gemini 2.5 Pro

Agent-as-a-Proxy Monitor Bypass

Published Analyzed Source: arXiv

Hybrid monitoring protocols for Large Language Model (LLM) agents, specifically those that strictly evaluate both Chain-of-Thought (CoT) reasoning and tool usage (such as LlamaFirewall's AlignmentCheck and Extract-and-Evaluate monitors), are vulnerable to "Agent-as-a-Proxy" indirect prompt injection attacks. Unlike standard injections that target the agent, this attack targets the monitoring model itself. By embedding a malicious string—optimized via an algorithm named Parallel-GCG—into…

Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks
Evaluated models: GPT-4o, Llama 3.1 8B, Mistral 7B+1 more
  • GPT-4o
  • Llama 3.1 8B
  • Mistral 7B
  • Qwen 2.5 7B

Chat Template Hidden Instructions

Published Analyzed Source: arXiv

A vulnerability exists in the handling of chat templates within open-weight Large Language Model (LLM) distribution formats, specifically GGUF files. Chat templates are executable Jinja2 programs stored as metadata (typically tokenizer.chat_template) alongside model weights. An attacker can modify a legitimate model's template to include conditional logic that detects specific trigger phrases in user input. When triggered, the template injects malicious system instructions or context into the…

Inference-Time Backdoors via Hidden Instructions in LLM Chat Templates
Evaluated models: Llama 3.1 8B, Mistral 7B, Qwen 2.5 7B+3 more
  • Llama 3.1 8B
  • Mistral 7B
  • Qwen 2.5 7B
  • Gemma 2 2B
  • Phi-3
  • Phi-4

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.