Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2508.16325
Cited By
v1
v2 (latest)
ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
22 August 2025
Darpan Aswal
Céline Hudelot
Re-assign community
ArXiv (abs)
PDF
HTML
Github (30252★)
Papers citing
"ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts"
0 / 0 papers shown
No papers found