176 citations · 186 across the 2 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CR2026
From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses
Simon Hegelich, Bardh Prenkaj, Habiba Sarhan +5
AI coding harnesses couple language models to shells, filesystems, and network sockets, turning the harness into an automated Living-off-the-Land (LotL) platform: once an adversary…
cs.AI2026
Co-Recursive Semantic Self-Extension: A Mathematical Foundation for Open-Ended Intelligence
Simon Hegelich, Bardh Prenkaj, Habiba Sarhan +5
Artificial intelligence has advanced through scale, data, and computation, yet remains bounded by its representational framework. We ask what makes intelligence open-ended. Every i…