Pith. sign in

Graph of attacks with pruning: Optimizing stealthy jailbreak prompt generation for enhanced llm content moderation

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 2 cs.CL 1

years

2026 2 2025 1

roles

background 1

polarities

background 1

representative citing papers

Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours

cs.AI · 2026-05-05 · unverdicted · novelty 6.0

An agentic red teaming system automates creation of adversarial testing workflows from natural language goals, unifying ML and generative AI attacks and achieving 85% success rate on Meta Llama Scout with no custom human code.

citing papers explorer

Showing 3 of 3 citing papers.