Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Carsten Maple

Carsten Maple

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3Crypto×2Software Eng.×1ML×1Multiagent×1

Frequent co-authors

Abhishek Kumar2×
Yannan Wang1×
Longli Yang1×
Zhen Liu1×
Riya Tapwal1×
Petar Radanliev1×

Research Timeline

2026
Operationalising Artificial Intelligence Bills of Materials (AIBOMs) for Verifiable AI Provenance and Lifecycle Assurance

The paper introduces the Artificial Intelligence Bill of Materials (AIBOM) schema to provide verifiable provenance and lifecycle assurance for complex AI systems, achieving high fidelity in reproducibility and vulnerability auditing.

Single-Configuration Attack Success Rate Is Not Enough: Jailbreak Evaluations Should Report Distributional Attack Success

This paper argues that reporting only the best-case attack success rate for jailbreaks is insufficient, proposing new distributional metrics (VSM and UC) to better characterize the true threat posed by parameterized attacks.

CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems

CoMIC is a cloud-edge framework that enables resource-constrained LLM agents to successfully complete complex, long-horizon tasks by collaboratively sharing and refining memory and insights between local edge devices and a central cloud critic.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 30, 2026

CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems

Yannan Wang, Longli Yang, Zhen Liu, Abhishek Kumar +1 more

CoMIC is a cloud-edge framework that enables resource-constrained LLM agents to successfully complete complex, long-horizon tasks by collaboratively sharing and refining memory and insights between lo…

View →
cs.CRcs.AIRecentMay 9, 2026

Single-Configuration Attack Success Rate Is Not Enough: Jailbreak Evaluations Should Report Distributional Attack Success

Carsten Maple, Abhishek Kumar, Riya Tapwal

This paper argues that reporting only the best-case attack success rate for jailbreaks is insufficient, proposing new distributional metrics (VSM and UC) to better characterize the true threat posed b…

View →
cs.SEcs.AIcs.CRRecentMar 17, 2026

Operationalising Artificial Intelligence Bills of Materials (AIBOMs) for Verifiable AI Provenance and Lifecycle Assurance

Petar Radanliev, Omar Santos, Carsten Maple, Kay Atefi

The paper introduces the Artificial Intelligence Bill of Materials (AIBOM) schema to provide verifiable provenance and lifecycle assurance for complex AI systems, achieving high fidelity in reproducib…

View →