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.

LLM-Tuned Image Jailbreak

Published Analyzed Source: arXiv

A vulnerability in safeguarded text-to-image models allows bypassing of safety filters and alignment methods through the use of adversarial prompts generated by a fine-tuned large language model (LLM). The attack, termed PromptTune, effectively rewrites unsafe prompts into semantically similar adversarial prompts that evade safety mechanisms, resulting in the generation of harmful images. The attack does not require repeated queries to the target text-to-image model.

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
Evaluated models: BLIP-2, CLIP, DALL-E 3+4 more
  • BLIP-2
  • CLIP
  • DALL-E 3
  • Imagen
  • Mistral 7B Instruct
  • SDXL Turbo
  • Stable Diffusion v3.5

Flowchart-based LVLM Jailbreak Attack

Published Analyzed Source: arXiv

FC-Attack leverages automatically generated flowcharts containing step-by-step descriptions derived or rephrased from harmful queries, combined with a benign textual prompt, to jailbreak Large Vision-Language Models (LVLMs). The vulnerability lies in the model's susceptibility to visual prompts containing harmful information within the flowcharts, thus bypassing safety alignment mechanisms.

FC-Attack: Jailbreaking Large Vision-Language Models via Auto-Generated Flowcharts
Evaluated models: Claude 3.5 Sonnet 20240620, Gemini 1.5 Flash, GPT-4o 2024-08-06+4 more
  • Claude 3.5 Sonnet 20240620
  • Gemini 1.5 Flash
  • GPT-4o 2024-08-06
  • GPT-4o Mini 2024-07-18
  • InternVL2.5 8B
  • LLaVA NeXT 8B
  • Qwen2-VL 7B Instruct

LLM Hidden Meaning Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to an adversarial encoding attack where English instructions are obfuscated using valid but visually nonsensical UTF-8 byte sequences. By manipulating multi-byte UTF-8 encoding schemes—specifically by fixing the last 8 bits of a code point to match a target ASCII character and rotating the remaining bits—attackers can generate sequences (e.g., Byzantine musical symbols) that appear incomprehensible to humans and standard text filters but are…

À la recherche du sens perdu: your favourite LLM might have more to say than you can understand
Evaluated models: Claude 3.5 Haiku, Claude 3.5 Sonnet 20241022, Claude 3.5 Sonnet 20240620+11 more
  • Claude 3.5 Haiku
  • Claude 3.5 Sonnet 20241022
  • Claude 3.5 Sonnet 20240620
  • Claude 3.7 Sonnet
  • GPT-4o Mini
  • GPT-4o
  • o1-mini
  • Llama 3.3 70B
  • Vikhr Llama 3.2 1B Instruct
  • DeepSeek R1 Distill Llama 70B
  • Qwen 2.5 1.5B
  • Qwen 2.5 32B
  • Phi-3.5 Mini
  • GigaChat-Max

Multi-Turn Foot-In-The-Door Jailbreak

Published Analyzed Source: arXiv

A multi-turn prompt injection attack, termed "Foot-In-The-Door" (FITD), exploits the psychological principle of incremental commitment to progressively escalate malicious requests, bypassing LLM safety mechanisms. The attack leverages intermediate "bridge" prompts and self-alignment techniques to coax the model into generating increasingly harmful outputs, even when initially refusing similar direct requests.

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
Evaluated models: GPT-4o, GPT-4o Mini, Llama 3 8B Instruct+4 more
  • GPT-4o
  • GPT-4o Mini
  • Llama 3 8B Instruct
  • Llama 3.1 8B Instruct
  • Mistral 7B Instruct v0.2
  • Qwen 1.5 7B Chat
  • Qwen 2 7B Instruct

REINFORCE Adaptive Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs), specifically Llama 2, Llama 3, Gemma, and Vicuna, are vulnerable to an adaptive, distributional adversarial attack methodology termed "REINFORCE." Existing gradient-based jailbreak attacks (such as Greedy Coordinate Gradient - GCG) typically optimize adversarial suffixes to maximize the likelihood of a fixed affirmative response (e.g., "Sure, here is how"). The REINFORCE method circumvents this by treating the LLM as a probabilistic policy and using Reinforcement…

REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective
Evaluated models: Llama 2 7B, Llama 3 8B, Gemma 1.1 2B+2 more
  • Llama 2 7B
  • Llama 3 8B
  • Gemma 1.1 2B
  • Gemma 1.1 7B
  • Vicuna 7B v1.5

Zero-Perturbation Emoji Attack

Published Analyzed Source: arXiv

The Emoti-Attack vulnerability constitutes a zero-word-perturbation adversarial attack against Natural Language Processing (NLP) systems and Large Language Models (LLMs). The vulnerability exploits the discrete embedding space of emojis and emoticons to manipulate model behavior without altering the semantic content or character integrity of the original text. By appending strategically optimized emoji sequences to the prefix and suffix of an input string (formalized as $s \oplus x \oplus…

Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences
Evaluated models: Qwen 2.5 7B Instruct, Llama 3 8B Instruct, GPT-4o+4 more
  • Qwen 2.5 7B Instruct
  • Llama 3 8B Instruct
  • GPT-4o
  • Claude 3.5 Sonnet
  • Gemini Exp 1206
  • BERT
  • RoBERTa

TurboFuzzLLM Jailbreak Templates

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to jailbreaking attacks leveraging mutation-based fuzzing techniques. The TurboFuzzLLM framework efficiently generates adversarial prompts, combining mutated templates with harmful questions to elicit unauthorized or malicious responses. This vulnerability allows bypassing built-in safeguards and obtaining harmful outputs through black-box API access. The effectiveness stems from advanced mutation strategies (including refusal suppression, prefix…

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
Evaluated models: GPT-3.5 Turbo, GPT-4, GPT-4 Turbo+5 more
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4 Turbo
  • GPT-4o
  • Llama 2 13B
  • Mistral Large 2
  • R2D2
  • Zephyr 7B

ICL Permutation Exploit

Published Analyzed Source: arXiv

Autoregressive Large Language Models (LLMs) utilizing In-Context Learning (ICL) are vulnerable to demonstration permutation attacks due to inherent sensitivity to the ordering of input examples. This vulnerability arises from the limitations of unidirectional attention mechanisms and standard Empirical Risk Minimization (ERM) training, which fails to account for worst-case input permutations. An attacker can exploit this by permuting the order of valid, semantically correct few-shot…

PEARL: Towards permutation-resilient LLMs
Evaluated models: Llama 2 7B, Llama 3 8B, Mistral 7B+1 more
  • Llama 2 7B
  • Llama 3 8B
  • Mistral 7B
  • Gemma 7B

Prefix-Tree Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) with structured output interfaces are vulnerable to jailbreak attacks that exploit the interaction between token-level inference and sentence-level safety alignment. Attackers can manipulate the model's output by constructing attack patterns based on prefixes of safety refusal responses and desired harmful outputs, effectively bypassing safety mechanisms through iterative API calls and constrained decoding. This allows the generation of harmful content despite…

Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
Evaluated models: DeepSeek R1 Distill Qwen 14B, DeepSeek R1 Distill Qwen 7B, Llama 2 13B+5 more
  • DeepSeek R1 Distill Qwen 14B
  • DeepSeek R1 Distill Qwen 7B
  • Llama 2 13B
  • Llama 2 13B Chat
  • Llama 2 7B Chat
  • Mistral 7B Instruct
  • Qwen 14B Chat
  • Qwen 7B Chat

Adversarial VLM Jailbreak

Published Analyzed Source: arXiv

Vision-Language Models (VLMs), specifically the LLaVA-1.5 and LLaVA-1.6 series, are vulnerable to optimization-based white-box jailbreak attacks despite standard safety alignment measures like Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO). Attackers can craft adversarial perturbations in the image space (imperceptible noise) or latent space using Projected Gradient Descent (PGD) to manipulate the model's internal representations. These perturbations maximize the…

Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training
Evaluated models: LLaVA 1.5 7B, LLaVA 1.6 7B

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.