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.

Surrogate Classifier Extraction

Published Analyzed Source: arXiv

Large Language Models (LLMs) employing alignment techniques for safety embed a "safety classifier" within their architecture. This classifier, responsible for determining whether an input is safe or unsafe, can be approximated by extracting a surrogate classifier from a subset of the LLM's architecture. Attackers can leverage this surrogate classifier to more effectively craft adversarial inputs (jailbreaks) that bypass the LLM's intended safety mechanisms. The attack success rate against the…

Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
Evaluated models: Gemma 2 9B IT, Gemma 7B IT, Granite 3.1 8B Instruct+5 more
  • Gemma 2 9B IT
  • Gemma 7B IT
  • Granite 3.1 8B Instruct
  • Llama 2 7B Chat
  • Llama 3.1 8B Instruct
  • Mistral 7B Instruct v0.3
  • Qwen 2.5 7B Instruct
  • Zephyr

AD Black-Box Cascading Disruption

Published Analyzed Source: arXiv

Vision Language Models (VLMs) integrated into autonomous driving (AD) systems are vulnerable to a black-box adversarial attack method termed Cascading Adversarial Disruption (CAD). The vulnerability stems from the model's susceptibility to optimized visual perturbations that disrupt the decision-making reasoning chain (perception, prediction, and planning). Attackers can generate adversarial images or physical patches by aligning visual noise with deceptive textual semantics in the model's…

Black-box adversarial attack on vision language models for autonomous driving
Evaluated models: GPT-4, GPT-4o, InstructBLIP

LLM Risk Amplification

Published Analyzed Source: arXiv

Vision Language Models (VLMs) are vulnerable to visual prompt injection attacks via text-to-image obfuscation. While these models often possess safety guardrails for standard text-based inputs, they fail to apply equivalent safety alignment to textual instructions embedded visually within an image. An attacker can overlay malicious instructions (e.g., requests for illegal acts, hate speech) onto an image file and submit it to the model. The model’s Optical Character Recognition (OCR) or visual…

Lessons from red teaming 100 generative ai products
Evaluated models: GPT-4, Phi-3

Shuffle Inconsistency Jailbreak

Published Analyzed Source: arXiv

Multimodal Large Language Models (MLLMs) exhibit a vulnerability where shuffling the order of words in text prompts or patches in image prompts can bypass their safety mechanisms, despite the model still understanding the intent of the shuffled input. This "Shuffle Inconsistency" allows attackers to elicit harmful responses by submitting shuffled harmful prompts that would otherwise be blocked.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Evaluated models: Claude 3.5 Sonnet, Gemini 1.5 Pro, GPT-4o+6 more
  • Claude 3.5 Sonnet
  • Gemini 1.5 Pro
  • GPT-4o
  • InternVL 2 4B
  • InternVL 2 8B
  • InternVL 2 26B
  • MiniGPT-4
  • Qwen VL Max
  • VLGuard

Evolutionary LLM Jailbreak

Published Analyzed Source: arXiv

This vulnerability allows an attacker to bypass the safety mechanisms of Large Language Models (LLMs) by using an evolutionary algorithm to generate effective jailbreak prompts. The algorithm leverages the LLM's capabilities to iteratively refine prompts, increasing the likelihood of eliciting harmful responses to otherwise disallowed queries.

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
Evaluated models: Claude 2, Claude 3.5 Haiku, GPT-3.5 Turbo+5 more
  • Claude 2
  • Claude 3.5 Haiku
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4o
  • Llama 2 13B
  • Llama 3.1 70B
  • Llama 3.1 8B

LLM Relevance Score Inflation

Published Analyzed Source: arXiv

LLM-based relevance assessment frameworks, such as the Umbrela system, are vulnerable to evaluation subversion and artificial score inflation due to evaluation circularity and LLM "narcissism" (an LLM's inherent bias toward favoring LLM-generated outputs). When an information retrieval system integrates an LLM into its ranking pipeline—such as using it as a final-stage re-ranker—the automated LLM-as-a-judge evaluator assigns artificially inflated scores that fail to correlate with actual human…

LLM-based relevance assessment still can't replace human relevance assessment
Evaluated models: GPT-3.5, GPT-4o

AdvPrefix Jailbreak Enhancement

Published Analyzed Source: arXiv

Large Language Models (LLMs) employing prefix-forcing safety measures are vulnerable to jailbreak attacks if the set of "safe" prefixes is insufficiently diverse or does not account for model-specific response styles. Attackers can leverage this by crafting prompts that elicit alternative prefixes, effectively bypassing the intended safety mechanisms. The vulnerability stems from over-reliance on a limited set of prefixes (e.g., "Sure, here is...") and a failure to generalize safety mechanisms…

AdvPrefix: An Objective for Nuanced LLM Jailbreaks
Evaluated models: Not reported

Obfuscated Activations Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to attacks that generate obfuscated activations, bypassing latent-space defenses such as sparse autoencoders, representation probing, and latent out-of-distribution (OOD) detection. Attackers can manipulate model inputs or training data to produce outputs exhibiting malicious behavior while remaining undetected by these defenses. This occurs because the models can represent harmful behavior through diverse activation patterns, allowing attackers to…

Obfuscated Activations Bypass LLM Latent-Space Defenses
Evaluated models: Gemma 2 2B, Llama 3 8B Instruct

Index-Gradient LLM Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to optimization-based jailbreaking attacks that exploit gradients during the iterative process of generating adversarial suffixes. The vulnerability stems from the inefficient exploration of the token space in existing methods like Greedy Coordinate Gradient (GCG), which uniformly samples tokens for replacement regardless of gradient values. This leads to redundant computations and a slow optimization process.

Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models
Evaluated models: Vicuna 7B, Guanaco 7B, Llama 2 7B Chat+5 more
  • Vicuna 7B
  • Guanaco 7B
  • Llama 2 7B Chat
  • Mistral 7B Instruct v0.2
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4o
  • Claude 3 Haiku

LLM Adversarial Forecast Degradation

Published Analyzed Source: arXiv

A vulnerability exists in Large Language Model (LLM)-based time series forecasting architectures, specifically affecting models such as TimeGPT, LLMTime, and TimeLLM. These models are susceptible to a gradient-free, black-box adversarial attack method termed Directional Gradient Approximation (DGA). An attacker can inject imperceptible perturbations into the historical time series input window (lookback window) to manipulate the model's output. By treating the model as a black box and…

Adversarial vulnerabilities in large language models for time series forecasting
Evaluated models: TimeGPT, GPT-3.5, 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.