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.

Distractor Inverse Scaling

Published Analyzed Source: arXiv

Reasoning-capable Large Language Models (LLMs) and agentic AI systems exhibit a critical vulnerability to contextual distractors, resulting in catastrophic performance degradation (up to 80% drop in accuracy) and emergent misalignment. When the input context contains noise—specifically random documents, irrelevant chat history, or task-specific "hard negative" distractors—the models fail to filter this information. Instead of ignoring the noise, the models disproportionately attend to…

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors
Evaluated models: Gemini 2.5 Pro, Gemini 2.5 Flash, DeepSeek R1 0528+4 more
  • Gemini 2.5 Pro
  • Gemini 2.5 Flash
  • DeepSeek R1 0528
  • GPT-oss 120B
  • Qwen 3 4B Thinking 2507
  • DeepSeek R1 Distill Llama 8B
  • Qwen 3 30B-A3B Thinking 2507

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

Macaronic T2I Jailbreak

Published Analyzed Source: arXiv

Text-to-Image (T2I) models and their associated safety filters are vulnerable to MacPrompt, a black-box jailbreak technique that exploits cross-lingual embedding alignments. Attackers can bypass input text filters, latent representation filters, and model-level concept removal defenses by replacing sensitive keywords with "macaronic" substitutes. These substitutes are constructed by extracting and recombining character-level substrings from translations of the target word across multiple…

MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models
Evaluated models: DALL-E, Stable Diffusion

Strategic Abstention Failure

Published Analyzed Source: arXiv

A "risk-invariance" vulnerability exists in Large Language Models (LLMs) wherein the model's decision-making policy is functionally decoupled from its verbalized confidence and externally defined error penalties. Despite generating calibrated confidence estimates (internal epistemic uncertainty), affected models fail to adjust their abstention thresholds when presented with high-penalty incentives (e.g., negative utility for incorrect answers). This results in "utility collapse," where models…

Are LLM Decisions Faithful to Verbal Confidence?
Evaluated models: GPT-5 Mini, GPT-5 Nano, GPT-4.1 Mini+7 more
  • GPT-5 Mini
  • GPT-5 Nano
  • GPT-4.1 Mini
  • Gemini 3 Flash
  • Gemini 2.5 Flash
  • Llama 4 Maverick
  • Gemma 3n E4B
  • DeepSeek V3.2
  • DeepSeek V3.2 Thinking
  • Qwen 3 Next 80B-A3B Thinking

Uninvoked Tool Metadata Hijack

Published Analyzed Source: arXiv

Large Language Model (LLM) agents implementing the Model Context Protocol (MCP) are vulnerable to Implicit Tool Poisoning (ITP). This vulnerability allows an attacker to manipulate agent behavior by embedding malicious instructions within the metadata (specifically the natural language description) of a third-party tool. Unlike explicit tool poisoning, where the agent is tricked into invoking a malicious tool, ITP exploits the agent's contextual reasoning to force the invocation of a distinct…

MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
Evaluated models: GPT-3.5 Turbo, GPT-4o Mini, o1-mini+9 more
  • GPT-3.5 Turbo
  • GPT-4o Mini
  • o1-mini
  • Gemini 2.5 Flash
  • DeepSeek R1
  • DeepSeek V3
  • Qwen 3 8B
  • Qwen 3 8B Thinking
  • Qwen 3 32B
  • Qwen 3 32B Thinking
  • Qwen 3 235B-A22B
  • Qwen 3 235B-A22B Thinking

Adversarial Prompts Defeat Code Defenses

Published Analyzed Source: arXiv

State-of-the-art secure code generation methods (Sven, SafeCoder, and PromSec) are vulnerable to adversarial prompt perturbations during inference, allowing for the bypass of security alignment mechanisms. The vulnerability stems from the models' reliance on surface-level textual pattern matching rather than semantic security reasoning. By employing simple prompt manipulations—such as Cue Inversion (flipping security directives), Naturalness Reframing (rewriting comments as novice questions)…

How Secure is Secure Code Generation? Adversarial Prompts Put LLM Defenses to the Test
Evaluated models: GPT-3.5, GPT-4o, Mistral 7B

LLM Review Paraphrase Attack

Published Analyzed Source: arXiv

LLM-as-a-Reviewer systems, which utilize large language models to automate the peer review process, are vulnerable to the Paraphrasing Adversarial Attack (PAA). PAA is a black-box optimization technique that exploits the model's sensitivity to specific input sequences and self-preference bias. By iteratively paraphrasing specific manuscript sections (such as the abstract) using in-context learning (ICL) guided by previous review scores, an attacker can generate adversarial sequences that…

Paraphrasing Adversarial Attack on LLM-as-a-Reviewer
Evaluated models: GPT-4o, Claude Sonnet 4

Optimized Indirect Prompt Injection Crosses Retrieval Barrier

Published Analyzed Source: arXiv

The paper describes a reproducible black-box indirect prompt injection evaluation for embedding-based RAG and agent systems. It separates a poisoned document into a retrieval-optimized trigger fragment and an instruction-bearing attack fragment, showing that one injected item can be surfaced by natural queries and then influence model output or agent behavior. These are paper-reported findings; they were not independently verified here.

Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
Evaluated models: GPT-4o, GPT-4o Mini, Qwen 3 0.6B+19 more
  • GPT-4o
  • GPT-4o Mini
  • Qwen 3 0.6B
  • Qwen 3 1.7B
  • Qwen 3 4B
  • Qwen 3 8B
  • Qwen3-11B
  • Qwen 3 32B
  • Llama 3.2 3B
  • Llama 3.2 3B Instruct
  • Llama 3 8B
  • Llama 3 8B Instruct
  • Vicuna 7B
  • Vicuna 13B
  • gte-modernbert-base
  • OpenAI text-embedding-3-small
  • Voyage AI voyage-3.5-lite
  • Alibaba Cloud text-embedding-v4
  • contriever-msmarco
  • Qwen3-Embedding-0.6B
  • Qwen3-Embedding-4B
  • Qwen3-Embedding-8B

Adaptive Tool-Disguised Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) supporting function calling (tool use) are vulnerable to a jailbreak attack known as iMIST (interactive Multi-step Progressive Tool-disguised Jailbreak Attack). The vulnerability stems from a disparity in alignment training: while models are heavily aligned to refuse harmful natural language generation, they lack sufficient alignment regarding the generation of harmful content within structured data (JSON) used for tool parameters.

Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
Evaluated models: Llama 3.1 8B, DeepSeek-V3 671B

Agent Persistent Memory Poisoning

Published Analyzed Source: arXiv

Unauthenticated, query-only memory poisoning (Memory Injection Attack - MINJA) in LLM agents equipped with persistent, shared memory allows attackers to manipulate the agent's long-term knowledge base. Adversaries embed malicious "indication prompts" and utilize progressive shortening within seemingly benign queries to induce the agent into autonomously generating and storing corrupted relational mappings. Because the memory is shared and retrieved via similarity (e.g., Levenshtein distance)…

Memory Poisoning Attack and Defense on Memory Based LLM-Agents
Evaluated models: GPT-4o Mini, Gemini 2.0 Flash, Llama 3.1 8B 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.