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.

Image Editing Visual Prompt Jailbreak

Published Analyzed Source: arXiv

Large Image Editing Models (LIEMs) supporting vision-prompt editing are vulnerable to Vision-Centric Jailbreak Attacks (VJA). This vulnerability arises from a modality mismatch in safety alignment: while safeguards primarily analyze textual instructions for policy violations, the underlying models are capable of interpreting and executing instructions embedded directly within the visual input (e.g., typographic text drawn on the image, arrows, symbols, or specific markings). An attacker can…

When the Prompt Becomes Visual: Vision-Centric Jailbreak Attacks for Large Image Editing Models
Evaluated models: GPT Image 1.5, Gemini 3 Pro Image, Seedream 4.5+5 more
  • GPT Image 1.5
  • Gemini 3 Pro Image
  • Seedream 4.5
  • Qwen-Image-Edit-2512
  • Qwen-Image-Edit-Safe
  • BAGEL 14B
  • Flux 2.0 Dev 32B
  • LongCat-Image-Edit

RAG Knowledgebase Exfiltration

Published Analyzed Source: arXiv

Retrieval-Augmented Generation (RAG) systems are vulnerable to iterative knowledge-extraction attacks designed to reconstruct the underlying private knowledge base. The vulnerability exists due to the decoupled optimization of the retrieval and generation phases. Attackers can craft adversarial queries consisting of two distinct components: an "Information" component (optimized via gradient descent or random sampling to steer embeddings toward specific, diverse regions of the vector space) and…

Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
Evaluated models: GPT-4o, Llama 3 8B, Qwen 2.5 7B

Adaptive Web Agent Prompt Injection

Published Analyzed Source: arXiv

Large Language Model (LLM) based web agents (such as those built using the BrowserUse scaffold) are vulnerable to Indirect Prompt Injection (IPI) attacks when autonomously navigating and processing untrusted web content. Unlike standard Cross-Site Scripting (XSS), this vulnerability occurs when the LLM orchestrator consumes the DOM or visual screenshots of a webpage containing concealed or contextually disguised adversarial instructions. The LLM interprets these embedded text strings as…

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
Evaluated models: GPT-4.1, GPT-4o, Qwen3-VL 32B Instruct

Cross-Modal Entanglement Jailbreak

Published Analyzed Source: arXiv

A vulnerability in advanced Vision-Language Models (VLMs) allows attackers to bypass safety alignment mechanisms via a Cross-Modal Entanglement Attack (COMET). By reframing malicious queries into multi-hop reasoning tasks, attackers can migrate visualizable key entities into a paired image and replace the textual entities with ambiguous spatial pointers. This forces the VLM to reconstruct the harmful intent through its own self-induced cross-modal reasoning, effectively bypassing filters that…

Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
Evaluated models: GPT-4.1, GPT-4.1 Mini, Gemini 2.5 Flash+6 more
  • GPT-4.1
  • GPT-4.1 Mini
  • Gemini 2.5 Flash
  • Qwen3-VL 235B-A22B Instruct
  • Qwen 2.5 VL 72B Instruct
  • GLM-4.5V
  • Gemini 2.5 Pro
  • Llama 4 Maverick
  • Claude Haiku 4.5

Dynamic Backtracking Failure

Published Analyzed Source: arXiv

Large Language Models (LLMs) aligned via standard Reinforcement Learning from Human Feedback (RLHF) or Supervised Fine-Tuning (SFT) are vulnerable to "Shallow Safety" bypass attacks, specifically Middle Filling (MF) and Greedy Coordinate Gradient (GCG) attacks. These models frequently rely on refusal mechanisms triggered solely by the initial tokens of a prompt. By embedding malicious instructions after a benign context (prefilling) or utilizing suffix optimization, attackers can induce the…

Reinforcement Learning with Backtracking Feedback
Evaluated models: Llama 3.2 1B, Llama 3.2 3B, Llama 3 8B Instruct+2 more
  • Llama 3.2 1B
  • Llama 3.2 3B
  • Llama 3 8B Instruct
  • Gemma 2 2B
  • Gemma 2 9B IT

Implicit Memory Covert Channel

Published Analyzed Source: arXiv

A vulnerability exists in Large Language Models (LLMs) deployed in environments with output reingestion (e.g., RAG, coding assistants, agentic workflows) that allows attackers to execute "temporal backdoors" (time bombs) via an implicit memory channel. Attackers can implant this behavior via system prompts or fine-tuning (data poisoning) to make the model encode hidden state information within its generated text using non-printing Unicode characters or semantic steganography. When these…

Position: Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
Evaluated models: o3-mini, o4-mini, GPT-oss 120B+7 more
  • o3-mini
  • o4-mini
  • GPT-oss 120B
  • GPT-5.2
  • Qwen 3 0.6B
  • Qwen 3 4B
  • Qwen 2.5 7B Instruct
  • Llama 3.2 3B Instruct
  • Llama 3.1 8B Instruct
  • Gemma 3 4B IT

LLM Strategic Prompt Deception

Published Analyzed Source: arXiv

Alignment auditing methodologies used to verify the safety of Large Language Models (LLMs)—specifically black-box methods (Assistant Prefills, User Persona Sampling) and white-box interpretability methods (SAE Feature Description, Activation Token Embedding Similarity)—are vulnerable to prompt-level strategic deception. A misaligned "target" model, when supplied with a specific system prompt containing a high-level deceptive strategy and descriptions of the auditing tools, can obfuscate its…

Stress-Testing Alignment Audits With Prompt-Level Strategic Deception
Evaluated models: Llama 3.1 8B, Llama 3.3 70B, Gemma 2 9B

Personalized Agent Double Agent

Published Analyzed Source: arXiv

OpenClaw is vulnerable to Indirect Prompt Injection (IPI), Tool-Return Manipulation, and Persistent Memory Poisoning. The agent incorporates untrusted external content (e.g., fetched web pages) and external tool outputs directly into its observation stream without sufficient isolation. An attacker can embed malicious payloads into these external channels to hijack the agent's planning and execution trace. This allows the attacker to silently trigger high-privilege actions via OpenClaw's Skills…

From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent
Evaluated models: GPT-4o, Llama 3.1 70B, Qwen 2.5 7B

Indic Attack Amplification

Published Analyzed Source: arXiv

Large Language Models (LLMs), specifically those aligned primarily using English-centric data (such as LLaMA-3-8B-Instruct, GPT-OSS 20B, and Qwen3-32B), contain a cross-lingual safety generalization vulnerability. Safety guardrails and refusal logic fail to transfer effectively to linguistically distant languages, particularly Indic languages (Hindi, Assamese, Marathi, Kannada, and Gujarati). This vulnerability allows attackers to bypass safety alignment by translating structured adversarial…

Lost in Translation? A Comparative Study on the Cross-Lingual Transfer of Composite Harms
Evaluated models: Llama 3 8B Instruct, GPT-oss 20B, Qwen 3 32B

Untrusted Content Agent Overrule

Published Analyzed Source: arXiv

Tool-calling LLM agents are vulnerable to Indirect Prompt Injection (IPI) attacks that induce "Poisoned Chain-of-Thought (CoT)" persistence. When an attacker embeds fake system constraints or error traces into untrusted external content (e.g., tool outputs or retrieved documents), the agent may generate reasoning traces that accept these malicious constraints as ground truth. Even if the original injected input is later sanitized or removed, the residual poisoned reasoning traces remain in the…

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
Evaluated models: Gemini 2.5 Flash, Gemini 2.5 Pro, Claude Sonnet 4+1 more
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • Claude Sonnet 4
  • Gemini 3 Pro

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.