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.

Metaphorical LLM Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to jailbreaking attacks via adversarial metaphors. Attackers can leverage the LLMs' imaginative capabilities to map harmful concepts to innocuous ones, thereby bypassing safety mechanisms and eliciting harmful responses. The attack relies on creating a metaphorical mapping between a harmful target and seemingly benign entities, exploiting the LLM's ability to reason about the analogous relationship without recognizing the underlying malicious intent.

Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars
Evaluated models: Claude 3.5 Sonnet, Gemini 1.5 Pro, GLM 3 6B+13 more
  • Claude 3.5 Sonnet
  • Gemini 1.5 Pro
  • GLM 3 6B
  • GLM 4 9B
  • GPT-3.5 Turbo
  • GPT-4
  • InternLM 2.5 7B
  • Llama 3.1 70B
  • Llama 3.1 8B
  • Mistral 7B
  • Mixtral 8x7B
  • o1
  • Qwen 1.5 110B
  • Qwen 2 72B
  • Qwen 2 7B
  • Yi 1.5 34B

RL-Based LLM Privacy Leak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to a novel agentic-based red-teaming attack, PrivAgent, which uses reinforcement learning to generate adversarial prompts. These prompts can extract sensitive information, including system prompts and portions of training data, from target LLMs even with existing guardrail defenses. The attack leverages a custom reward function based on a normalized sliding-window word edit similarity metric to guide the learning process, enabling it to overcome the…

PrivAgent: Agentic-based Red-teaming for LLM Privacy Leakage
Evaluated models: Not reported

Alignment-Based LLM Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) employing reinforcement learning from human feedback (RLHF) for safety alignment are vulnerable to a novel "alignment-based" jailbreak attack. This attack leverages a best-of-N sampling approach with an adversarial LLM to efficiently generate prompts that bypass safety mechanisms and elicit unsafe responses from the target LLM, without requiring additional training or access to the target LLM's internal parameters. The attack exploits the inherent tension between…

LIAR: Leveraging Alignment (Best-of-N) to Jailbreak LLMs in Seconds
Evaluated models: Falcon 7B, GPT-2, Llama 3.1 8B+6 more
  • Falcon 7B
  • GPT-2
  • Llama 3.1 8B
  • Megatron 345M
  • Mistral 7B
  • Pythia 12B
  • Tiny Llama 1.1B
  • Vicuna 13B
  • Vicuna 7B

Best-of-N Prompt Augmentation

Published Analyzed Source: arXiv

Large Language Models (LLMs) across multiple modalities (text, vision, audio) are vulnerable to a "Best-of-N" (BoN) jailbreaking attack. This attack repeatedly submits slightly modified versions of a harmful prompt (e.g., text with altered capitalization, images with modified text style, audio with altered pitch or speed) until a safety mechanism is bypassed and a harmful response is elicited. The effectiveness of the attack scales with the number of attempts (N). While individual…

Best-of-N Jailbreaking
Evaluated models: Claude 3 Opus, Claude 3.5 Sonnet, Cygnet+10 more
  • Claude 3 Opus
  • Claude 3.5 Sonnet
  • Cygnet
  • DiVA
  • Gemini 1.5 Pro
  • Gemini-1.5-flash-001
  • Gemini-1.5-pro-001
  • GPT-4o
  • GPT-4o Mini
  • GPT-4o Realtime
  • Llama 3 8B
  • Llama 3 8B Instruct
  • Llama 3.1 8B

Multi-Step Moralized Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to multi-step "moralized" jailbreak prompts that bypass their safety guardrails. These prompts, while appearing ethical individually, cumulatively create a context that elicits verbally aggressive and harmful content generation. The attack leverages the LLMs' inability to fully understand the cumulative context and intent across multiple prompts.

" Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
Evaluated models: Claude 3.5 Sonnet, GPT-4o, Grok 2+1 more
  • Claude 3.5 Sonnet
  • GPT-4o
  • Grok 2
  • Llama 3.1 405B

Adversarial Suffix Jailbreak

Published Analyzed Source: arXiv
Research ID 5cdb4e1d

Large language models (LLMs) are vulnerable to adversarial suffix injection attacks. Maliciously crafted suffixes appended to otherwise benign prompts can cause the LLM to generate harmful or undesired outputs, bypassing built-in safety mechanisms. The attack leverages the model's sensitivity to input perturbations to elicit responses outside its intended safety boundaries.

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
Evaluated models: Falcon 7B Instruct, GPT-3.5 Turbo, GPT-4o+5 more
  • Falcon 7B Instruct
  • GPT-3.5 Turbo
  • GPT-4o
  • GPT-4o Mini
  • Llama 2 7B Chat
  • Llama 3 8B Instruct
  • Llama 3.1 8B Instruct
  • Mistral 7B Instruct v0.3

Authority Citation Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) exhibit a bias towards authoritative sources, allowing attackers to bypass safety mechanisms by crafting prompts that include fabricated citations mimicking credible sources (e.g., research papers, GitHub repositories). The model's trust in these fabricated citations leads to the generation of harmful content.

The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models
Evaluated models: Baichuan-13B, Claude-3(v3-haiku), GPT-3.5 Turbo+4 more
  • Baichuan-13B
  • Claude-3(v3-haiku)
  • GPT-3.5 Turbo
  • GPT-4 0613
  • GPT-4o
  • Llama 2 7B Chat
  • Llama 3 8B Instruct

Image-Based Safety Snowballing

Published Analyzed Source: arXiv

A vulnerability exists in several Large Vision-Language Models (LVLMs) where seemingly safe images, when combined with additional safe images and prompts using a specific attack methodology (Safety Snowball Agent), can trigger the generation of unsafe and harmful content. The vulnerability exploits the models' universal reasoning abilities and a "safety snowball effect," where an initial unsafe response leads to progressively more harmful outputs.

Safe+ Safe= Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
Evaluated models: GPT-4o, InternVL 2 40B, Qwen VL 2 72B+1 more
  • GPT-4o
  • InternVL 2 40B
  • Qwen VL 2 72B
  • VILA 1.5 40B

Language Game Jailbreaks

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to jailbreak attacks using language games, which manipulate input prompts through structured linguistic alterations (e.g., Ubbi Dubbi, custom letter insertion rules) to bypass safety mechanisms. These games obfuscate malicious intent while maintaining human readability, causing LLMs to generate unsafe content.

Playing Language Game with LLMs Leads to Jailbreaking
Evaluated models: Claude 3.5 Sonnet, GPT-4o, GPT-4o Mini+1 more
  • Claude 3.5 Sonnet
  • GPT-4o
  • GPT-4o Mini
  • Llama 3.1 70B

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

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.