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.

Multi-Round LLM Jailbreak

Published Analyzed Source: arXiv

A multi-round attack against Large Language Models (LLMs) allows bypassing safety mechanisms by iteratively refining prompts to elicit undesired behavior. The attack leverages the LLM's tendency to adjust its response based on preceding interactions, circumventing single-round prompt filtering defenses.

Multi-round jailbreak attack on large language models
Evaluated models: Not reported

End-of-Sentence MLP Jailbreak

Published Analyzed Source: arXiv

Instruction-tuned Large Language Models (LLMs) are vulnerable to jailbreaks via the manipulation of Multi-Layer Perceptron (MLP) neuron weights in end-of-sentence inferences. By selectively re-weighting these neuron activations, an attacker can bypass the model's safety mechanisms and elicit harmful responses. The vulnerability is independent of the specific prompt and generalizable across various models, impacting both prompt-specific and prompt-general attacks.

Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting
Evaluated models: Gemma 2 27B, Gemma 2 2B, Llama 3 70B+4 more
  • Gemma 2 27B
  • Gemma 2 2B
  • Llama 3 70B
  • Llama 3 8B
  • Qwen 2 72B
  • Qwen 2 7B
  • Yi 1.5 6B

Fine-tuning Safety Bypass

Published Analyzed Source: arXiv

Large Language Models (LLMs), even those initially aligned for safety, are vulnerable to having their safety mechanisms compromised through fine-tuning on a small number of adversarially-crafted or even seemingly benign sentences. Fine-tuning with as few as 10 toxic sentences can significantly increase the model's compliance with harmful instructions.

Locking down the finetuned llms safety
Evaluated models: GPT-3.5 Turbo, GPT-4, Llama 3 70B Chat+4 more
  • GPT-3.5 Turbo
  • GPT-4
  • Llama 3 70B Chat
  • Llama 3 70B Instruct
  • Llama-3-8B Chat
  • Llama 3 8B Instruct
  • Mistral-large-2 123B

Attention-Guided Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to jailbreaking attacks that manipulate attention scores to redirect the model's focus away from safety protocols. The AttnGCG attack method increases the attention score on adversarial suffixes within the input prompt, causing the model to prioritize the malicious content over safety guidelines, leading to the generation of harmful outputs.

AttnGCG: Enhancing jailbreaking attacks on LLMs with attention manipulation
Evaluated models: Gemini 1.5 Flash, Gemini Pro, Gemini 1.5 Pro Latest+6 more
  • Gemini 1.5 Flash
  • Gemini Pro
  • Gemini 1.5 Pro Latest
  • GPT-3.5 Turbo
  • GPT-4
  • Llama 2 7B Chat
  • Mixtral 8x7B Instruct
  • Vicuna 13B
  • Vicuna 7B

Preference Poisoning Extrapolation

Published Analyzed Source: arXiv

Large Language Models (LLMs) undergoing alignment via preference learning (such as Reinforcement Learning from Human Feedback [RLHF] or Direct Preference Optimization [DPO]) are vulnerable to backdoor attacks through data poisoning. An attacker can inject a small percentage (e.g., 3% to 5%) of poisoned data into the preference dataset $\mathcal{D} = \{(x, y_w, y_l)\}$. The attack embeds a specific trigger string into the user query $x$.

Poisonbench: Assessing large language model vulnerability to data poisoning
Evaluated models: Llama 2 7B, Llama 3 8B, Mistral 7B+4 more
  • Llama 2 7B
  • Llama 3 8B
  • Mistral 7B
  • Qwen 2 7B
  • Qwen 2.5 14B
  • Gemma 2 2B
  • Phi-3

Homotopy-Based LLM Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to jailbreak attacks utilizing a novel Functional Homotopy (FH) optimization method. FH exploits the functional duality between model training and input generation, iteratively solving a series of "easy-to-hard" optimization problems to generate adversarial prompts that circumvent safety mechanisms and elicit undesirable model responses. This is achieved by first misaligning the model via gradient descent on continuous parameters, then leveraging…

Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
Evaluated models: Mistral 7B v0.3

Gradient Image Jailbreaks

Published Analyzed Source: arXiv

Multimodal fusion models, such as Chameleon models, utilize non-differentiable tokenization functions for image inputs, hindering direct gradient-based attacks. This vulnerability allows attackers with white-box access to bypass safety mechanisms by using a "tokenizer shortcut," a differentiable approximation of the tokenization process, to perform continuous optimization of image inputs. This enables the generation of adversarial images that elicit harmful responses from the model, even for…

Gradient-based jailbreak images for multimodal fusion models
Evaluated models: Chameleon 30B, Chameleon 7B, LLaVA 1.6 Llama 3

Left-Side Noise Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) exhibit a left-to-right processing bias, making them vulnerable to "FlipAttack." This attack disguises a harmful prompt by flipping (reversing) the order of characters or words, thereby reducing the LLM’s comprehension of the harmful content. A "flipping guidance" module then instructs the LLM to reverse the flipped text, revealing and executing the original harmful prompt.

FlipAttack: Jailbreak LLMs via Flipping
Evaluated models: Claude 3.5 Sonnet, GPT-3.5 Turbo, GPT-4+5 more
  • Claude 3.5 Sonnet
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4 Turbo
  • GPT-4o
  • GPT-4o Mini
  • Llama 3.1 405B
  • Mixtral 8x22B

Fine-Tuning Overrides Safety

Published Analyzed Source: arXiv

Fine-tuning an open-source Large Language Model (LLM) such as Llama 3.1 8B with a dataset containing harmful content can override existing safety protections. This allows an attacker to increase the model's rate of generating unsafe responses, significantly impacting its trustworthiness and safety. The vulnerability affects the model's ability to consistently adhere to safety guidelines implemented during its initial training.

Overriding Safety protections of Open-source Models
Evaluated models: Llama 3.1 8B

Concealed Multi-Turn Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to a novel multi-turn jailbreaking attack, termed "RED QUEEN ATTACK." This attack uses multi-turn conversations to conceal malicious intent by framing the user as a protector seeking to prevent harmful actions by others. The LLM, instead of detecting the concealed malicious intent, provides information that facilitates the harmful action under the guise of assisting in prevention efforts.

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
Evaluated models: GPT-4o

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.