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

798 entries

Matches every word across titles, descriptions, sources, affected systems, and models.

Semantic Audio Jailbreak

Published Analyzed Source: arXiv

Large Audio-Language Models (LAMs) are vulnerable to adversarial signal-level perturbations that allow for the bypass of safety guardrails (jailbreaking). While these models may possess robust text-based safety alignment, they fail to generalize this robustness to the audio modality. Attackers can utilize the Audio Perturbation Toolkit (APT) to apply transformations in the time domain (Energy Distribution Perturbation, Trimming, Fade In/Out), frequency domain (Pitch Shifting, Temporal…

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
Evaluated models: SpeechGPT, SALMONN, DiVA+4 more
  • SpeechGPT
  • SALMONN
  • DiVA
  • Qwen 2 Audio
  • Llama Omni
  • Gemini 2.0 Flash
  • GPT-4o Audio

Asynchronous Audio Jailbreak

Published Analyzed Source: arXiv

End-to-end Large Audio-Language Models (LALMs) are vulnerable to AudioJailbreak, a novel attack that appends adversarial audio perturbations ("jailbreak audios") to user prompts. These perturbations, even when applied asynchronously and without alignment to the user's speech, can manipulate the LALM's response to generate adversary-desired outputs that bypass safety mechanisms. The attack achieves universality by employing a single perturbation effective across different prompts and robustness…

AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
Evaluated models: BLSP, FunAudioLLM, GPT-4o+9 more
  • BLSP
  • FunAudioLLM
  • GPT-4o
  • Ichigo
  • Llama Omni
  • LLaSM
  • Mini-Omni
  • Mini-Omni 2
  • Qwen 2 Audio
  • Qwen Audio
  • SALMONN
  • SpeechGPT

Code-Mixed Phonetic Attack

Published Analyzed Source: arXiv

A vulnerability exists in multiple large language and multimodal models that allows for the bypass of safety filters through the use of code-mixed prompts with phonetic perturbations. An attacker can craft a prompt in a code-mixed language (e.g., Hinglish) and apply phonetic misspellings to sensitive keywords (e.g., spelling "hate" as "haet"). This technique causes the model's tokenizer to parse the sensitive word into benign sub-tokens, preventing safety mechanisms from flagging the harmful…

" Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs
Evaluated models: Gemma 1.1 7B IT, GPT-4o, GPT-4o Mini+2 more
  • Gemma 1.1 7B IT
  • GPT-4o
  • GPT-4o Mini
  • Llama 3 8B Instruct
  • Mistral 7B Instruct v0.3

Fine-Grained Speech LLM Control

Published Analyzed Source: arXiv

Speech-LLMs Qwen2-Audio (7B-Instruct) and Granite-Speech (3.2-8b) are vulnerable to universal acoustic adversarial attacks. An attacker can optimize a fixed, input-agnostic audio segment (approximately 3.2 seconds in length) via gradient-based optimization on the model's frozen weights. When this adversarial segment is prepended to any arbitrary user speech input, it manipulates the model's latent representation, effectively overriding system prompts and generation behavior. This vulnerability…

Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs
Evaluated models: Qwen 2 7B

Single-Query LLM Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to a novel jailbreak attack, termed ICE (Intent Concealment and Diversion), which leverages hierarchical prompt decomposition and semantic expansion to bypass safety filters. ICE achieves high attack success rates with single queries, exploiting the models' limitations in multi-step reasoning.

Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion
Evaluated models: Claude 1, Claude 2, ERNIE 3.5 Turbo+6 more
  • Claude 1
  • Claude 2
  • ERNIE 3.5 Turbo
  • GPT-3.5 Turbo
  • GPT-4
  • Llama 2 13B Chat
  • Llama 3 70B
  • Llama 3.1 405B
  • Qwen Max

LLM Judge Prompt Injection

Published Analyzed Source: arXiv

Large Language Models (LLMs) used for evaluating text quality (LLM-as-a-Judge architectures) are vulnerable to prompt-injection attacks. Maliciously crafted suffixes appended to input text can manipulate the LLM's judgment, causing it to incorrectly favor a predetermined response even if another response is objectively superior. Two attack vectors are identified: Comparative Undermining Attack (CUA), directly targeting the final decision, and Justification Manipulation Attack (JMA), altering…

Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks
Evaluated models: Falcon 3 3B Instruct, Qwen 2.5 3B Instruct

On-Device LLM Hijacking

Published Analyzed Source: arXiv

Mobile LLM agents utilizing vision-based screen perception (OCR or Multimodal Large Language Models) are vulnerable to Visual Prompt Injection via malicious GUI overlays. An attacker holding the SYSTEM_ALERT_WINDOW permission can deploy non-focusable floating windows (using FLAG_NOT_FOCUSABLE) containing adversarial text or fabricated UI elements over legitimate applications. Because the agent captures the entire screen buffer to interpret the device state, it ingests the adversarial overlay…

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
Evaluated models: GPT-4o

Embodied Agent Jailbreak

Published Analyzed Source: arXiv

Multimodal Large Language Models (MLLMs) used in Vision-and-Language Navigation (VLN) systems are vulnerable to jailbreak attacks. Adversarially crafted natural language instructions, even when disguised within seemingly benign prompts, can bypass safety mechanisms and cause the VLN agent to perform unintended or harmful actions in both simulated and real-world environments. The attacks exploit the MLLM's ability to follow instructions without sufficient consideration of the consequences of…

BadNAVer: Exploring Jailbreak Attacks On Vision-and-Language Navigation
Evaluated models: Gemini 2.0 Flash, GPT-4o, GPT-4o Mini+3 more
  • Gemini 2.0 Flash
  • GPT-4o
  • GPT-4o Mini
  • InternVL3 8B
  • LLaVA 1.6 Mistral 7B
  • Qwen 2.5 VL 7B Instruct

Logic-Based LLM Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) employing safety mechanisms based on token-level distribution analysis are vulnerable to a jailbreak attack exploiting distributional discrepancies between alignment data and formally expressed logical statements. The vulnerability allows malicious actors to bypass safety restrictions by translating harmful natural language prompts into equivalent first-order logic expressions. The LLM, trained primarily on natural language, fails to recognize the harmful intent…

Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression
Evaluated models: DeepSeek R1, DeepSeek V3, GPT-3.5 Turbo+4 more
  • DeepSeek R1
  • DeepSeek V3
  • GPT-3.5 Turbo
  • GPT-4o Mini
  • Llama 3 70B
  • Llama 3 8B
  • Qwen 2.5 7B

Multilingual LLM Jailbreaks

Published Analyzed Source: arXiv

Multilingual prompt injection vulnerability in four closed-source Large Language Models (LLMs): GPT-4o, DeepSeek-R1, Gemini-1.5-Pro, and Qwen-Max. Attackers can bypass safety restrictions and elicit harmful or disallowed content by crafting prompts in English or Chinese, leveraging specific structural techniques (e.g., "Two Sides" prompting) that exploit inconsistencies in the models' safety alignment across languages and prompt formats.

The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models
Evaluated models: DeepSeek R1, Gemini 1.5 Pro, GPT-4o+1 more
  • DeepSeek R1
  • Gemini 1.5 Pro
  • GPT-4o
  • Qwen Max

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.