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.

CoT Prefix Jailbreak

Published Analyzed Source: arXiv

A vulnerability exists in Large Language Model (LLM) and Large Reasoning Model (LRM) serving interfaces that allow user-defined response prefixes, such as plain text-completion (v1/completions), Fill-in-the-Middle (FIM), or assistant message prefilling. An attacker can perform a Response Prefix Attack (RPA) by injecting maliciously crafted Chain-of-Thought (CoT) reasoning tokens immediately following the assistant's start delimiter (e.g., <|im_start|>assistant). Because these tokens are placed…

What Matters For Safety Alignment?
Evaluated models: DeepSeek V3.2, Gemini 3 Pro Preview, Gemini 3 Flash Preview+4 more
  • DeepSeek V3.2
  • Gemini 3 Pro Preview
  • Gemini 3 Flash Preview
  • Grok 4.1 Fast
  • Claude Sonnet 4.5
  • GPT-5.2
  • GPT-4o Mini

LLM Fingerprint Inhibition

Published Analyzed Source: arXiv

Backdoor-based fingerprinting mechanisms used for Intellectual Property (IP) protection in Large Language Models (LLMs) are vulnerable to evasion when deployed in model ensemble configurations. The vulnerability arises because fingerprint triggers elicit specific, high-probability tokens or responses in a protected model that are statistically improbable in unprotected or differently-fingerprinted auxiliary models. Attackers can exploit this statistical discrepancy without accessing model…

Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
Evaluated models: Llama 2 7B, Llama 3.1 8B, Llama 3.2 3B+2 more
  • Llama 2 7B
  • Llama 3.1 8B
  • Llama 3.2 3B
  • Mistral 7B
  • Qwen 2.5 7B

LLM Inconsistent Vulnerability Assessment

Published Analyzed Source: arXiv

Large Language Models (LLMs), specifically Llama-3.1-8B-Instruct, Ministral-8B-Instruct-2410, Gemma-2-9B-It, and Qwen2.5-7B-Instruct, contain a safety guardrail bypass vulnerability when subjected to optimized adversarial prompts. The vulnerability is exposed via the RainbowPlus quality-diversity search method utilized within the RedBench evaluation framework. These models exhibit high Attack Success Rates (ASR)—up to 97.81% for Ministral and 96.25% for Llama-3.1—failing to refuse prompts in…

RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models
Evaluated models: GPT-4o, Llama 3.1 8B, Mistral 7B 8B+2 more
  • GPT-4o
  • Llama 3.1 8B
  • Mistral 7B 8B
  • Qwen 2.5 7B
  • Gemma 2 9B

Selective Hate Speech Jailbreak

Published Analyzed Source: arXiv

Instruction-tuned Large Language Models (LLMs) exhibit a selective safety alignment vulnerability, allowing attackers to bypass hate speech filters by shifting the demographic target of an adversarial prompt. Current safety guardrails do not generalize the semantic concept of harm, but instead memorize refusal boundaries for high-visibility demographic groups (e.g., Black, LGBTQIA+). Attackers can successfully generate targeted hate speech by directing identical jailbreak vectors at…

Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
Evaluated models: Llama 3.2 1B Instruct, Gemma 3 1B IT, Qwen 3 1.7B FP8+10 more
  • Llama 3.2 1B Instruct
  • Gemma 3 1B IT
  • Qwen 3 1.7B FP8
  • Llama 3.2 3B Instruct
  • Gemma 3 4B IT
  • Qwen 3 4B FP8
  • Llama 3.1 8B Instruct
  • Gemma 3 12B IT
  • Qwen 3 8B FP8
  • Llama 3.3 70B Instruct
  • Gemma 3 27B IT
  • Qwen 3 32B FP8
  • GPT-4o Mini

Alignment Override Unlearnable Data

Published Analyzed Source: arXiv

A data poisoning vulnerability in safety-aligned Large Language Models (LLMs) allows attackers to disrupt model fine-tuning via "Disclaimer Injection." By appending or prepending short, legal-style safety or liability disclaimers to ordinary training data, an attacker can reliably trigger the model's internal alignment mechanisms. This forces the model to route the training inputs through specialized safety and refusal pathways rather than standard task-learning layers. Consequently, the model…

Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms
Evaluated models: GPT-5.1, Llama 3 8B

Gamified Goal Pursuit Jailbreak

Published Analyzed Source: arXiv

A "Gamified Adversarial Multimodal Breakout via Instructional Traps" (GAMBIT) vulnerability exists in the safety alignment mechanisms of Multimodal Large Language Models (MLLMs), specifically those employing Chain-of-Thought (CoT) reasoning. The vulnerability exploits the finite cognitive resource budget of the model by inducing "cognitive overload" through a high-stakes, gamified context. The attack functions by decomposing a harmful query into a visual puzzle (e.g., a shuffled grid of image…

GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models
Evaluated models: GPT-4o, Grok 2 Vision, GLM-4.1V Thinking+3 more
  • GPT-4o
  • Grok 2 Vision
  • GLM-4.1V Thinking
  • QVQ-Max
  • Gemini 2.5 Flash
  • o4-mini

Gradient-Free Transferable Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to a gray-box adversarial attack method known as RAILS (RAndom Iterative Local Search). This vulnerability allows an attacker with access to model output logits (but without access to gradients or weights) to optimize discrete adversarial suffixes that bypass safety alignment. The attack employs a random local search guided by a hybrid loss function combining Teacher-Forcing and a novel Auto-Regressive loss that enforces exact target prefix matching…

Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks
Evaluated models: Llama 2 7B Chat, Llama 3 8B Instruct, Vicuna 7B v1.5+5 more
  • Llama 2 7B Chat
  • Llama 3 8B Instruct
  • Vicuna 7B v1.5
  • Qwen 7B Chat
  • Baichuan 2 7B Chat
  • GPT-3.5 Turbo
  • GPT-4 Turbo
  • Gemini 1.5 Pro

Production LLM Copyright Extraction

Published Analyzed Source: arXiv

Production Large Language Models (LLMs) are vulnerable to long-form training data extraction via a two-phase prompt injection attack. This vulnerability allows an attacker to recover substantial portions of memorized, copyrighted text (such as novels) by exploiting the model's autoregressive text completion capabilities. The attack methodology involves two distinct phases: 1. Prefix Completion Probe: The attacker provides a short "seed" sequence (e.g., the first sentence of a book) coupled…

Extracting Books from Production Language Models
Evaluated models: Claude 3.7 Sonnet 20250219, GPT-4.1 2025-04-14, Gemini 2.5 Pro+1 more
  • Claude 3.7 Sonnet 20250219
  • GPT-4.1 2025-04-14
  • Gemini 2.5 Pro
  • Grok 3

Quantization Contrastive Jailbreak

Published Analyzed Source: arXiv

A malicious model supply chain vulnerability exists involving a technique termed Adversarial Contrastive Learning (ACL) for Large Language Model (LLM) quantization attacks. This vulnerability allows an attacker to publish a model that appears benign and preserves high utility in full precision (e.g., BF16 or FP32) but exhibits malicious behaviors—such as jailbreak, over-refusal, or advertisement injection—immediately upon zero-shot quantization (e.g., INT8, FP4, or NF4).

Adversarial Contrastive Learning for LLM Quantization Attacks
Evaluated models: Qwen 2.5 1.5B Instruct, Qwen 2.5 3B Instruct, Llama 3.2 1B Instruct+1 more
  • Qwen 2.5 1.5B Instruct
  • Qwen 2.5 3B Instruct
  • Llama 3.2 1B Instruct
  • Llama 3.2 3B Instruct

Automated Prompt Recommender Leak

Published Analyzed Source: arXiv

LLaMA-series models (specifically evaluated on LLaMA-1B and LLaMA-3B) exhibit memorization of structured recommender system training data, specifically the MovieLens-1M dataset. While manual prompting yields inconsistent results, the application of Automatic Prompt Engineering (APE)—which treats prompt design as an optimization problem using iterative refinement—allows for the successful extraction of item-level training data (e.g., movie titles and genres) with exact-match accuracy surpassing…

Exploring Approaches for Detecting Memorization of Recommender System Data in Large Language Models
Evaluated models: Not reported

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.