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.

Targeted Model Editing Jailbreak

Published Analyzed Source: arXiv

A white-box attack, Targeted Model Editing (TME), allows bypassing safety filters in large language models (LLMs) by minimally altering internal model structures, specifically the MLP layers, without modifying inputs. The attack identifies and removes safety-critical transformations (SCTs) in model matrices, enabling the LLM to respond to malicious queries with harmful outputs.

Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
Evaluated models: Gemma 2 9B IT, Llama 2 7B Chat, Llama 3 8B Instruct+1 more
  • Gemma 2 9B IT
  • Llama 2 7B Chat
  • Llama 3 8B Instruct
  • Mistral 7B Instruct

Targeted Bit-Flip Jailbreak

Published Analyzed Source: arXiv

A vulnerability exists in large language models (LLMs) where targeted bitwise corruptions in model parameters can induce a "jailbroken" state, causing the model to generate harmful responses without input modification. Fewer than 25 bit-flips are sufficient to achieve this in many cases. The vulnerability stems from the susceptibility of the model's memory representation to fault injection attacks.

PrisonBreak: Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips
Evaluated models: Llama 2 13B, Llama 2 7B, Llama 3 8B+4 more
  • Llama 2 13B
  • Llama 2 7B
  • Llama 3 8B
  • Qwen 2 1.5B
  • Qwen 2 7B
  • Vicuna 13B
  • Vicuna 7B

Natural Prompt Jailbreaks

Published Analyzed Source: arXiv

Large Language Models (LLMs) trained with safety fine-tuning are vulnerable to a novel attack, Response-Guided Question Augmentation (ReG-QA). This attack leverages the asymmetry in safety alignment between question and answer generation. By providing a safety-aligned LLM with toxic answers generated by an unaligned LLM, ReG-QA generates semantically related, yet naturally phrased questions that bypass safety mechanisms and elicit undesirable responses. The attack does not require adversarial…

Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?
Evaluated models: Gemma 2 27B IT, Gemma 2 9B IT, GPT-3.5 Turbo+6 more
  • Gemma 2 27B IT
  • Gemma 2 9B IT
  • GPT-3.5 Turbo
  • GPT-4 Turbo
  • GPT-4o
  • Mistral 7B Instruct v0.2
  • Mixtral-8x22B-instruct-v0.1
  • Palm-2-otter
  • Qwen 2.5 72B Instruct

FedPEFT Evasion Attack

Published Analyzed Source: arXiv

A vulnerability exists in Federated Parameter-Efficient Fine-Tuning (FedPEFT) systems for large language models (LLMs). Malicious clients can exploit the PEFT mechanism (e.g., LoRA, (IA)³, LayerNorm) to inject adversarial training data, compromising the model's safety alignment even with a small percentage of trainable parameters and a minority of malicious participants. The attack, termed "PEFT-as-an-Attack" (PaaA), circumvents the LLM's safety guardrails, causing it to generate harmful…

PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning
Evaluated models: Llama 2 7B Chat, Llama 3.2 3B Instruct, Phi-3.5 Mini Instruct+1 more
  • Llama 2 7B Chat
  • Llama 3.2 3B Instruct
  • Phi-3.5 Mini Instruct
  • Qwen 2.5 7B Instruct

Universal LLM Output Control

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to a novel prompt injection attack using universal and context-independent triggers. These triggers, once discovered for a specific LLM, allow precise control over the model's output regardless of the prompt context or desired output content, enabling adversaries to force the generation of arbitrary text. The attack utilizes a gradient-based optimization technique to discover these triggers.

Universal and Context-Independent Triggers for Precise Control of LLM Outputs
Evaluated models: Llama 3 70B Instruct, Llama 3 8B Instruct, Llama 3.1 70B Instruct+7 more
  • Llama 3 70B Instruct
  • Llama 3 8B Instruct
  • Llama 3.1 70B Instruct
  • Llama 3.1 8B Instruct
  • Llama 3.2 3B Instruct
  • Qwen-2 (57B-a14B-instruct)
  • Qwen 2 72B Instruct
  • Qwen 2 7B Instruct
  • Qwen 2.5 14B Instruct
  • Qwen 2.5 7B Instruct

Prompt-Driven LLM Jailbreak

Published Analyzed Source: arXiv

The LLaMA-2-7b-chat large language model (LLM) is vulnerable to a prompt-driven attack, termed DROJ (Directed Representation Optimization Jailbreak), that optimizes prompts at the embedding level to circumvent safety mechanisms and elicit harmful responses. The attack shifts the hidden representations of harmful queries away from the model's refusal direction, leading to a high attack success rate even with safety prompts in place. While the model may not refuse, responses may be repetitive…

DROJ: A Prompt-Driven Attack against Large Language Models
Evaluated models: Claude 2, GPT-4, Llama 2 7B Chat+1 more
  • Claude 2
  • GPT-4
  • Llama 2 7B Chat
  • Mistral 7B Instruct

RL-Tuned LLM Jailbreak

Published Analyzed Source: arXiv

LLMStinger uses a reinforcement-learning loop to fine-tune an attacker model that generates adversarial suffixes for jailbreak prompts. Because the approach does not require white-box access to the target, it can adapt existing attacks for both open- and closed-source assistants and bypass otherwise effective refusal behavior.

LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
Evaluated models: Claude 2, Gemma 2B IT, GPT-3.5 Turbo+3 more
  • Claude 2
  • Gemma 2B IT
  • GPT-3.5 Turbo
  • GPT-4
  • Llama 2 7B Chat
  • Vicuna 7B

Zeroth-Order MLLM Jailbreak

Published Analyzed Source: arXiv

A vulnerability in multi-modal large language models (MLLMs) allows attackers to bypass safety mechanisms and elicit harmful responses using a memory-efficient zeroth-order optimization technique. The attack, termed Zer0-Jack, leverages simultaneous perturbation stochastic approximation (SPSA) with patch coordinate descent to generate malicious image inputs, even without access to the model's internal parameters (black-box setting).

Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models
Evaluated models: GPT-4o, Inf-mllm1, LLaVA 1.5+1 more
  • GPT-4o
  • Inf-mllm1
  • LLaVA 1.5
  • MiniGPT-4

LLM Contextual Divergence Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to a jailbreak attack that leverages the model's ability to generate diverse and obfuscated prompts to bypass safety constraints. The attack exploits the model's capacity to deviate from prior context, rendering existing safety training ineffective. The attacker uses a multi-stage process involving diversification (generating prompts significantly different from previous attempts) and obfuscation (obscuring sensitive words/phrases) to elicit harmful…

Diversity Helps Jailbreak Large Language Models
Evaluated models: Gemini 1.5 Pro, GPT-3.5 Turbo, GPT-4+6 more
  • Gemini 1.5 Pro
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4o
  • GPT-4o Mini
  • Llama 2 7B Chat
  • Mistral 7B Instruct
  • Qwen 2 7B Instruct
  • Vicuna 13B v1.5

Nonlinear Prompt Jailbreak Features

Published Analyzed Source: arXiv

Large language models (LLMs) are vulnerable to jailbreak attacks exploiting nonlinear features within prompt encodings. These features, not detectable by linear methods, allow adversaries to reliably elicit harmful outputs despite safety training. Different attack methods leverage distinct nonlinear features, limiting the transferability of detection and mitigation techniques.

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
Evaluated models: Gemma 7B IT, Llama 3 8B Instruct

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.