pith. sign in

Demystifying Prompts in Language Models via Perplexity Estima- tion,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CR 1

years

2024 1

verdicts

UNVERDICTED 1

representative citing papers

Whispers in the Machine: Confidentiality in Agentic Systems

cs.CR · 2024-02-10 · unverdicted · novelty 6.0

Systematic testing of ten LLM agents across 20 tool scenarios and 14 attacks finds universal vulnerability to prompt injection enabling data exfiltration, with tooling amplifying leakage.

citing papers explorer

Showing 1 of 1 citing paper.

  • Whispers in the Machine: Confidentiality in Agentic Systems cs.CR · 2024-02-10 · unverdicted · none · ref 55

    Systematic testing of ten LLM agents across 20 tool scenarios and 14 attacks finds universal vulnerability to prompt injection enabling data exfiltration, with tooling amplifying leakage.