RESEARCHInvestigateNEXT 12 MONTHS
Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks
arXiv cs.LG — Machine Learning
Factual evidence
What the source reports
Researchers propose a pre-processing defense to close the 'decode gap' where encoded or imaged text bypasses Vision-Language Model safety guards.
Open source