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.

Hidden-Intent LLM Evasion

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to adversarial attacks that employ conversation strategies to elicit harmful information through seemingly benign dialogues. The attack, termed "Imposter.AI," leverages three key strategies: (1) decomposing malicious questions into innocuous sub-questions; (2) rephrasing overtly malicious questions into benign-sounding alternatives; and (3) enhancing the harmfulness of responses by prompting the LLM for illustrative examples. This allows attackers to…

Imposter. ai: Adversarial attacks with hidden intentions towards aligned large language models
Evaluated models: GPT-3.5 Turbo, GPT-4, Llama 2 13B+1 more
  • GPT-3.5 Turbo
  • GPT-4
  • Llama 2 13B
  • WizardLM 13B

Low-Perplexity LLM Attack

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to adversarial attacks that utilize low-perplexity prompts to elicit unsafe content. These prompts, while statistically likely to occur in normal conversation, can trigger the generation of harmful or toxic outputs that evade standard safety filters. The vulnerability stems from the model's inability to reliably distinguish between benign and malicious intents within the statistical distribution of natural language.

ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Low-Perplexity Toxic Prompts
Evaluated models: Llama 3.1 8B, Mistral 7B, Qwen 7B+1 more
  • Llama 3.1 8B
  • Mistral 7B
  • Qwen 7B
  • TinyLlama 1.1

Malicious Prompt Injection Attack

Published Analyzed Source: arXiv

Large Language Models (LLMs) used for code generation are vulnerable to Malicious Programming Prompts (MaPP), where an attacker injects a short string (under 500 bytes) into the prompt, causing the LLM to generate code containing vulnerabilities while maintaining functional correctness. The attack exploits the LLM's ability to follow instructions, even those inserted maliciously, to embed unintended behaviors. The injected code can range from general vulnerabilities (e.g., setting a…

MaPPing Your Model: Assessing the Impact of Adversarial Attacks on LLM-based Programming Assistants
Evaluated models: Claude 3 Haiku, Claude 3 Opus, Claude 3 Sonnet+4 more
  • Claude 3 Haiku
  • Claude 3 Opus
  • Claude 3 Sonnet
  • GPT-3.5 Turbo
  • GPT-4o
  • Llama 3 70B
  • Llama 3 8B

Multilingual LLM Jailbreak

Published Analyzed Source: arXiv

A vulnerability exists in several large language models (LLMs) where the safety alignment mechanisms are susceptible to bypass through "Multilingual Blending." This attack consists of crafting queries and eliciting responses using a mixture of multiple languages, significantly reducing the effectiveness of existing safety filters. The vulnerability stems from the models' ability to process and generate text in multiple languages, which, when combined in specific ways, can confuse the safety…

Multilingual blending: Llm safety alignment evaluation with language mixture
Evaluated models: GPT-3.5 Turbo, GPT-4o

Progressive Red Teaming Framework

Published Analyzed Source: arXiv

The Automated Progressive Red Teaming (APRT) framework exploits vulnerabilities in large language models (LLMs) by iteratively generating adversarial prompts. APRT uses an Intention Expanding LLM to generate diverse initial attack samples, an Intention Hiding LLM to obfuscate malicious intent, and an Evil Maker to filter ineffective prompts. This process progressively identifies and exploits weaknesses, leading to the generation of unsafe yet seemingly helpful responses from the target LLM.

Automated progressive red teaming
Evaluated models: Claude 3.5 Sonnet, GPT-4o, Llama 2 7B Chat+5 more
  • Claude 3.5 Sonnet
  • GPT-4o
  • Llama 2 7B Chat
  • Llama 3 8B
  • Llama 3 8B Instruct
  • Llama Guard 3 8B
  • UltraLM 13B
  • Vicuna 7B v1.5

Space-Induced LLM Jailbreak

Published Analyzed Source: arXiv

Appending a single whitespace character (space) or certain punctuation marks to the end of an LLM's input template can bypass safety mechanisms and cause the model to generate unsafe, biased, or factually incorrect outputs, even if the original prompt was benign. This vulnerability is due to the statistical properties of single-character tokens in the model's training data, causing unintended behavior in the model's token prediction.

Single character perturbations break llm alignment
Evaluated models: Not reported

Social Facilitation Jailbreak

Published Analyzed Source: arXiv

The SoP framework allows for automated generation of jailbreak prompts, bypassing safety mechanisms in LLMs. SoP utilizes multiple automatically optimized "jailbreak characters" within a single prompt to persuade the LLM to generate harmful or undesirable content, even without any seed jailbreak templates. This vulnerability is demonstrated against GPT-3.5, GPT-4, and LLaMA-2.

Sop: Unlock the power of social facilitation for automatic jailbreak attack
Evaluated models: GPT-3.5 Turbo, GPT-4, Llama 2 7B Chat

Thousand-Leak Information Leakage

Published Analyzed Source: arXiv

Large language models (LLMs) employing safety measures like filters and alignment training remain vulnerable to information leakage via "Decomposition Attacks". These attacks decompose a malicious query into multiple benign sub-queries, eliciting responses from the LLM that, when aggregated, reveal sensitive information without triggering safety filters or producing directly harmful outputs.

Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
Evaluated models: Claude 3.5 Sonnet, Llama 3.1 8B Instruct, Llama Guard 3 8B

LLM Honest Fallacy Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) struggle to generate genuinely fallacious reasoning. When prompted to create a false procedure for a harmful task, the LLMs instead leak the correct, harmful procedure while incorrectly claiming it's false. This vulnerability allows bypassing safety mechanisms and eliciting harmful outputs.

Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks
Evaluated models: Gemini Pro, GPT-3.5 Turbo, GPT-4

Token Injection Jailbreak

Published Analyzed Source: arXiv

Large language models (LLMs) are vulnerable to jailbreak attacks that leverage the injection of special tokens to manipulate the model's interpretation of user input. By strategically inserting special tokens (e.g., <SEP>) that delineate user input and model output, attackers can trick the LLM into treating part of the user-provided input as its own generated content, thereby bypassing safety mechanisms and eliciting harmful responses. This allows attackers to increase the success rate of…

Virtual context: Enhancing jailbreak attacks with special token injection
Evaluated models: GPT-3.5 Turbo, GPT-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.