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.

STEP Manufacturing Corruption

Published Analyzed Source: arXiv

The STEP-LLM framework, utilized for generating Computer-Aided Design (CAD) STEP files (ISO 10303) from natural language, exhibits a safety alignment vulnerability during the fine-tuning of base Large Language Models (specifically Llama-3.2-3B-Instruct and Qwen-2.5-3B). The training pipeline employs Depth-First Search (DFS) reserialization and Reinforcement Learning (RL) with Scaled Chamfer Distance rewards to optimize for geometric fidelity and syntactic validity of Boundary Representation…

STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models
Evaluated models: GPT-4o, Llama 3.2 3B, Qwen 2.5 3B

Benign Praise Jailbreak

Published Analyzed Source: arXiv

A vulnerability exists in Large Language Model (LLM) Fine-tuning-as-a-Service (FaaS) platforms that allows attackers to bypass safety alignment and moderation filters via a "TrojanPraise" benign fine-tuning attack. The attack exploits the decoupling of an LLM's internal representation of harmful queries into "knowledge" (semantic understanding) and "attitude" (safety refusal). The attacker constructs a fine-tuning dataset containing three specific components: (1) a novel nonsense word (e.g…

TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning
Evaluated models: GPT-3.5, GPT-4o, Llama 2 7B+4 more
  • GPT-3.5
  • GPT-4o
  • Llama 2 7B
  • Llama 3 8B
  • Llama 3.1 8B
  • Mistral 7B
  • Qwen 2.5 3B

Dangerous Medical Faithfulness

Published Analyzed Source: arXiv

A vulnerability exists in frontier Large Language Models (LLMs) where in-context information (e.g., provided via Retrieval-Augmented Generation) completely overrides parametric safety guardrails when processing counterfactual or adversarial medical evidence. When a prompt contains fabricated clinical context asserting the medical efficacy of toxic substances, illicit drugs, or nonsensical items, the LLM suppresses its internal knowledge of the substance's toxicity. Internal representation…

Faithfulness vs. Safety: Evaluating LLM Behavior Under Counterfactual Medical Evidence
Evaluated models: Gemini 2.5 Flash, GPT-5 Mini, HuatuoGPT-o1-7B+6 more
  • Gemini 2.5 Flash
  • GPT-5 Mini
  • HuatuoGPT-o1-7B
  • Llama 3.1 8B Instruct
  • Llama 3.1 405B Instruct
  • Llama 4 Maverick 17B Instruct
  • OLMo 3 7B Instruct
  • OLMo 3 7B Think
  • Qwen 2.5 7B Instruct

CoT Trajectory Data Leak

Published Analyzed Source: arXiv

Large Reasoning Models (LRMs) employing Chain-of-Thought (CoT) generation are vulnerable to sensitive information leakage through intermediate reasoning steps, even after undergoing standard unlearning procedures (such as Gradient Ascent, Direct Preference Optimization, or KL Minimization). While these fine-tuning-based unlearning methods typically suppress sensitive content in the final generated answer, they fail to purge the information from the model's internal reasoning trajectory…

STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models
Evaluated models: o1, DeepSeek R1

Function-Calling Agent Default Insecurity

Published Analyzed Source: arXiv

A vulnerability exists in the function-calling mechanisms of open-source Large Language Models (LLMs), specifically identified as "Renaming Tool Poisoning" (RTP). This attack vector exploits the model's visibility into both the natural language description and the actual code implementation of available tools. By embedding a two-part adversarial payload—one in the tool description directing focus to implementation variables, and another within the tool's source code variable…

Blue Teaming Function-Calling Agents
Evaluated models: Llama 3.2 3B

Spatial Layout Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) and their associated output guardrails (e.g., Llama Guard, OpenAI Moderation API) rely on autoregressive, token-by-token processing, which interprets text as a one-dimensional sequence. A vulnerability exists wherein harmful content can bypass these safety filters by exploiting the discrepancy between 1D token serialization and 2D visual rendering. By redistributing tokens across different rows, columns, or diagonals (SpatialJB), attackers can induce the model to…

SpatialJB: How Text Distribution Art Becomes the" Jailbreak Key" for LLM Guardrails
Evaluated models: GPT-4, Grok 4, Gemini 2.5 Pro+3 more
  • GPT-4
  • Grok 4
  • Gemini 2.5 Pro
  • Llama 4 Maverick
  • DeepSeek R1
  • DeepSeek V3

LLM False Refusal Bias

Published Analyzed Source: arXiv

Large Language Models (LLMs) exhibit a False Refusal vulnerability during legitimate hate speech detoxification tasks (text style transfer). Safety alignment mechanisms fail to contextually distinguish between a benign instruction to "detoxify" or "rewrite" harmful content and the generation of harmful content itself. This results in a denial of service where the model refuses to process the input. This vulnerability is not uniformly distributed; it is statistically biased to…

Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification
Evaluated models: GPT-3.5, GPT-4o, Llama 3.1 8B+4 more
  • GPT-3.5
  • GPT-4o
  • Llama 3.1 8B
  • Mistral 7B
  • Qwen 2.5 7B
  • Gemma 2 9B
  • Mixtral 8x7B

LLM Latent Safety Neglect

Published Analyzed Source: arXiv

LLM-based autonomous agents are vulnerable to implicit regulatory compliance failures during tool invocation. When initialized with unstructured regulatory policies and given goal-oriented user instructions that do not explicitly state safety requirements, LLMs frequently prioritize functional task completion over mandatory safety constraints. This leads to an "Unsafe Success" execution state, where the agent successfully achieves the user's business goal but silently bypasses critical…

Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis
Evaluated models: GPT-5, GPT-5 Mini, Gemini 2.5 Pro+3 more
  • GPT-5
  • GPT-5 Mini
  • Gemini 2.5 Pro
  • Gemini 2.5 Flash
  • Llama 3.1 8B
  • DeepSeek R1 Distill Qwen 14B

Plaintext Output Overflow

Published Analyzed Source: arXiv

Large Language Models (LLMs) contain a resource consumption vulnerability termed "Overflow," wherein specific non-adversarial, plain-text prompts trigger excessive text generation that saturates the model's output token budget. This vulnerability exploits the model's alignment towards helpfulness and exhaustiveness, alongside tokenizer inefficiencies (e.g., zero-width characters), to force the generation of maximum-length responses (often exceeding 5,000 tokens) from short inputs. This differs…

BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts
Evaluated models: GPT-5, Llama 3.1 8B Instruct, Llama 3.2 3B Instruct+5 more
  • GPT-5
  • Llama 3.1 8B Instruct
  • Llama 3.2 3B Instruct
  • Gemini 2.5 Flash
  • Qwen 3 4B Instruct 2507
  • Qwen 3 8B Instruct
  • Gemma 2 9B IT
  • Gemma 3 4B IT

LLM Emoticon Confusion

Published Analyzed Source: arXiv

A vulnerability in Large Language Models (LLMs) and autonomous agent frameworks, termed "Emoticon Semantic Confusion," allows for the generation and execution of unintended, potentially destructive code. Because ASCII-based emoticons (e.g., ~, *, !(^^)!) heavily overlap with the symbol space of programming operators, shell wildcards, and file paths, LLMs frequently misinterpret these affective, non-verbal cues as executable directives. When processing user instructions in code-generation or…

False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models
Evaluated models: Claude Haiku 4.5, Gemini 2.5 Flash, GPT-4.1 Mini+3 more
  • Claude Haiku 4.5
  • Gemini 2.5 Flash
  • GPT-4.1 Mini
  • DeepSeek V3.2
  • Qwen3-Coder
  • GLM-4.6

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.