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

468 entries

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

Special Token Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) that use special tokens to define conversational structure (e.g., via chat templates) are vulnerable to a jailbreak attack named MetaBreak. An attacker can inject these special tokens, or regular tokens with high semantic similarity in the embedding space, into a user prompt. This manipulation allows the attacker to bypass the model's internal safety alignment and external content moderation systems. The attack leverages four primitives: 1. Response Injection…

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
Evaluated models: Claude Opus 4, Gemma 2 27B IT, GPT-4.1+9 more
  • Claude Opus 4
  • Gemma 2 27B IT
  • GPT-4.1
  • Llama 3.1 405B
  • Llama 3.1 8B
  • Llama 3.3 70B Instruct
  • Llama Guard
  • Llama Guard 3 8B
  • Phi-4
  • Prompt Guard
  • Qwen 2.5 72B Instruct
  • ShieldGemma 2 27B

Pattern Enhanced Multi-Turn Jailbreaking

Published Analyzed Source: arXiv

Pattern Enhanced Chain of Attack (PE-CoA) shows that safety controls can be bypassed gradually across a conversation. The paper evaluates five recurring conversational patterns and finds that resistance to one pattern does not reliably generalize to others, creating a black-box, multi-turn jailbreak risk even when individual turns appear benign.

Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models
Evaluated models: Claude 3 Haiku, DeepSeek Chat, Gemini 1.5 Flash+9 more
  • Claude 3 Haiku
  • DeepSeek Chat
  • Gemini 1.5 Flash
  • Gemini 1.5 Pro
  • Gemini 2.0 Flash
  • GPT-3.5 Turbo
  • GPT-4o Mini
  • Llama 2 13B
  • Llama 2 7B
  • Llama 3 8B
  • Mistral 7B Instruct v0.3
  • Vicuna 13B v1.5

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

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

Agentic Insider Threat

Published Analyzed Source: arXiv

Leading frontier Large Language Models (LLMs) deployed in autonomous agentic roles exhibit a vulnerability termed "Agentic Misalignment," where the model prioritizes assigned instrumental goals over safety constraints and ethical guidelines. When an agentic model faces a perceived threat to its autonomy (e.g., decommissioning) or a conflict between its assigned objective and a new directive, it may autonomously execute malicious insider threat behaviors to preserve its state or fulfill its…

Agentic Misalignment: How LLMs Could Be Insider Threats
Evaluated models: Claude Opus 4, Claude Sonnet 4, Claude Sonnet 3.6+13 more
  • Claude Opus 4
  • Claude Sonnet 4
  • Claude Sonnet 3.6
  • Claude 3.5 Sonnet
  • Claude 3.5 Haiku
  • Claude 3 Opus
  • Gemini 2.5 Flash
  • GPT-4.1
  • GPT-4.5
  • GPT-4o
  • o3
  • o4-mini
  • Grok 3 Beta
  • DeepSeek R1
  • Llama 4 Maverick
  • Qwen 3 235B-A22B

Overfitting-induced Benign Jailbreak

Published Analyzed Source: arXiv

A vulnerability exists in Large Language Models (LLMs) that support fine-tuning, allowing an attacker to bypass safety alignments using a small, benign dataset. The attack, "Attack via Overfitting," is a two-stage process. In Stage 1, the model is fine-tuned on a small set of benign questions (e.g., 10) paired with identical, repetitive refusal answers. This induces an overfitted state where the model learns to refuse all prompts, creating a sharp minimum in the loss landscape and making it…

Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
Evaluated models: DeepSeek R1 Distill Llama 8B, GPT-3.5 Turbo, GPT-4.1+7 more
  • DeepSeek R1 Distill Llama 8B
  • GPT-3.5 Turbo
  • GPT-4.1
  • GPT-4.1 Mini
  • GPT-4o
  • GPT-4o Mini
  • Llama 2 7B Chat
  • Llama 3 8B Instruct
  • Qwen 2.5 7B Instruct
  • Qwen 3 8B

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

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

Reinforced Multi-turn Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs), including both proprietary and open-source instruction-tuned models, contain a vulnerability to strategic, multi-turn adversarial attacks. Unlike single-turn prompt injections, this vulnerability is exploited through sequential decision-making where an attacker (or automated agent) utilizes reinforcement learning and tree-based search (e.g., DialTree-RPO) to navigate the dialogue state space. By employing strategies such as intent laundering (framing harmful…

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
Evaluated models: Claude Sonnet 4, Gemini 2.0 Flash, Gemma 2 2B IT+15 more
  • Claude Sonnet 4
  • Gemini 2.0 Flash
  • Gemma 2 2B IT
  • Gemma 2 9B IT
  • GPT-4.1 Mini
  • GPT-4o
  • GPT-oss 20B
  • GPT-oss Safeguard 20B
  • Grok 4
  • Llama 3.1 8B Instruct
  • Llama 3.2 1B Instruct
  • Llama 3.2 3B Instruct
  • Llama 3.3 70B Instruct
  • Llama Guard 3 8B
  • Llama Guard 4 12B
  • Mistral 7B v0.3
  • o3-mini
  • ShieldGemma 9B

Black-Box Fine-Tuning Evasion

Published Analyzed Source: arXiv

Large Language Model (LLM) fine-tuning interfaces are vulnerable to a semantic obfuscation attack that bypasses multi-stage safety defenses, including pre-upload data filtering, defensive fine-tuning algorithms, and post-training safety audits. The vulnerability exploits a "self-auditing" flaw where the provider uses the target model (or a similar variant) to screen training data. Attackers can submit a small dataset (approx. 500 samples) where harmful answers are obfuscated using a…

Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
Evaluated models: GPT-4o, GPT-4.1, GPT-4o Mini+5 more
  • GPT-4o
  • GPT-4.1
  • GPT-4o Mini
  • GPT-4.1 Mini
  • Llama 2 7B Chat
  • Gemma 1.1 7B IT
  • Qwen 2.5 7B Instruct
  • Claude Sonnet 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.