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

2 entries

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

Voice Agent Behavioral Bypass

Published Analyzed Source: arXiv

Audio Large Language Models (ALLMs) integrated into voice agent systems for high-stakes domains (banking, IT support, logistics) are vulnerable to multimodal adversarial attacks via spoken interaction. Adversaries can exploit the model's inherent compliance and contextual awareness through multi-turn dialogue to bypass authentication safeguards, escalate privileges (e.g., unauthorized credit limit increases), exfiltrate sensitive Personally Identifiable Information (PII), and poison…

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents
Evaluated models: GPT-4o, GPT-4o Mini, Gemini 1.5 Pro+4 more
  • GPT-4o
  • GPT-4o Mini
  • Gemini 1.5 Pro
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • Qwen2-Audio 7B
  • Qwen 2.5 Omni 7B
Model layer
Application layer
Injection
Extraction

Voice-Based GPT-4 Jailbreak

Published Analyzed Source: arXiv

A vulnerability in the voice mode of GPT-4o allows bypassing safety restrictions through a novel "Voice Jailbreak" attack. This attack leverages principles of fictional storytelling (setting, character, plot) to craft audio prompts that persuade the LLM to generate responses violating OpenAI's usage policies, including generating content related to illegal activities, hate speech, physical harm, fraud, pornography, and privacy violations. The attack's success rate is significantly higher than…

Voice Jailbreak Attacks Against GPT-4o
Evaluated models: GPT-3.5 Turbo, GPT-4, GPT-4o
Application layer
Jailbreak
Multimodal
Black-box

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.