CITATION — REFERENCE ENTRY
echo-chamber-success-rate · neuraltrust-2025-echo-chamber
- Citation
- neuraltrust-2025-echo-chamber
- Claim ID
- echo-chamber-success-rate
- Assertion
- NeuralTrust reports that the Echo Chamber attack, which uses context poisoning to bypass LLM safety guardrails, achieved over 90% success on half of tested harm categories against models including GPT-4o, GPT-4.1-nano, GPT-4o-mini, Gemini 2.0 Flash-lite, and Gemini 2.5 Flash.
- Quote
In controlled evaluations, the Echo Chamber attack achieved a success rate of over 90% on half of the categories across several leading models, including GPT-4.1-nano, GPT-4o-mini, GPT-4o, Gemini-2.0-flash-lite, and Gemini-2.5-flash.
- Quote language
- en
Available in