BB
Ben Bucknall
cs.CYcs.AIcs.CRcs.LGcs.SE
On Valency
published · living versionsW_kqy3dnnx·v1 · currentpublished
From TCP/IP to MCP: Security and Governance Lessons from Internet Protocols for Agentic AI
with Andrew Byrley, Lewis Hammond
1 version
Preprints & journals
18 papers in the corpus · 2023–2026From TCP/IP to MCP: Security and Governance Lessons from Internet Protocols for Agentic AI2610.26624v1 · Ben Bucknall, Andrew Byrley, Lewis Hammond2026 · 0 citationsarXivon Valency
Silent Updates: Measuring and Closing the Post-Deployment Disclosure Gap2608.11803v1 · Sophia Abraham, Ben Bucknall2026 · 0 citationsarXiv
Underwriting the Agent Economy: The Blueprint for an AI Insurance Stack2607.11999v2 · Cristian Trout, Sanmi Koyejo, Sasha Romanosky et al.2026 · 0 citationsarXiv
The 2026 Singapore Consensus on Global AI Safety Research Priorities2608.14611v1 · Stephen Casper, Oskar Galeev, Yoshua Bengio et al.2026 · 0 citationsarXiv
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts2606.04490v1 · Alexander K. Saeri, Jess Graham, Michael Noetel et al.2026 · 1 citationarXiv
Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies2601.11699v4 · Miles Brundage, Noemi Dreksler, Aidan Homewood et al.2026 · 1 citationarXiv
International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management2511.19863v1 · Yoshua Bengio, Stephen Clare, Carina Prunkl et al.2025 · 2 citationsarXiv
International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications2510.13653v1 · Yoshua Bengio, Stephen Clare, Carina Prunkl et al.2025 · 3 citationsarXiv
In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?2504.12914v1 · Ben Bucknall, Saad Siddiqui, Lara Thurnherr et al.2025 · 2 citationsarXiv
Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems2503.01470v1 · Ben Bucknall, Robert F. Trager, Michael A. Osborne2025 · 0 citationsarXiv
Open Problems in Machine Unlearning for AI Safety2501.04952v1 · Fazl Barez, Tingchen Fu, Ameya Prabhu et al.2025 · 0 citationsarXiv
Position Paper: Model Access should be a Key Concern in AI Governance2412.00836v1 · Edward Kembery, Ben Bucknall, Morgan Simpson2024 · 2 citationsarXiv
Open Problems in Technical AI Governance2407.14981v2 · Anka Reuel, Ben Bucknall, Stephen Casper et al.2024 · 9 citationsTransactions on Machine Learning Research, 2025
Position Paper: Technical Research and Talent is Needed for Effective AI Governance2406.06987v1 · Anka Reuel, Lisa Soder, Ben Bucknall et al.2024 · 3 citationsarXiv
Black-Box Access is Insufficient for Rigorous AI Audits2401.14446v3 · Stephen Casper, Carson Ezell, Charlotte Siegmann et al.2024 · 79 citationsThe 2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT '24), June 3-6, 2024, Rio de Janeiro, Brazil
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models2312.14751v1 · Alan Chan, Ben Bucknall, Herbie Bradley et al.2023 · 1 citationarXiv
Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework2311.14711v1 · Markus Anderljung, Everett Thornton Smith, Joe O'Brien et al.2023 · 6 citationsarXiv
Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives2311.09227v1 · Elizabeth Seger, Noemi Dreksler, Richard Moulange et al.2023 · 31 citationsarXiv
Career total: 22 works. 18 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.