Across four attack types, six of eight tested LLMs were successfully injected in at least one category, and GPT-4o failed every test.
A novel system for strengthening security in large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs
Across four attack types, six of eight tested LLMs were successfully injected in at least one category, and GPT-4o failed every test.