ICML 2025 Workshop TAIG Submissions

Technical Requirements for Halting Dangerous AI Activities
Peter Barnett, Aaron Scher, David Abecassis
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Proofs of Autonomy: Scalable and Practical Verification of AI Autonomy
Artem Grigor, Christian Schroeder de Witt, Ivan Martinovic
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Guaranteeable Memory: An HBM-Based Chiplet for Verifiable AI Workloads
James Petrie
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Trends in AI Supercomputers
Konstantin Friedemann Pilz, James Sanders, Robi Rahman, Lennart Heim
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Oral
- Readers: Everyone
Detecting Compute Structuring in AI Governance is likely feasible
Emmanouil Seferis, Timothy Fist
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Hardware-Enabled Mechanisms for Verifying Responsible AI Development
Aidan O'Gara, Gabriel Kulp, Will Hodgkins, James Petrie, Vincent Immler, Aydin Aysu, Kanad Basu, Shivam Bhasin, Stjepan Picek, Ankur Srivastava
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Oral
- Readers: Everyone
LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries
Zekun Wu, Seonglae Cho, Umar Mohammed, CRISTIAN ENRIQUE MUNOZ VILLALOBOS, Kleyton Da Costa, Xin Guan, Theo King, Ze Wang, Emre Kazim, Adriano Koshiyama
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Probing Evaluation Awareness of Language Models
Jord Nguyen, Hoang Huu Khiem, Carlo Leonardo Attubato, Felix Hofstätter
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Compute Requirements for Algorithmic Innovation in Frontier AI Models
Peter Barnett
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
AI Benchmarks: Interdisciplinary Issues and Policy Considerations
Maria Eriksson, Erasmo Purificato, Arman Noroozian, João Vinagre, Guillaume Chaslot, Emilia Gomez, David Fernández-Llorca
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
The Strong, weak and benign Goodhart's law. An independence-free and paradigm-agnostic formalisation
Adrien Majka, El-Mahdi El-Mhamdi
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Locking Open Weight Models with Spectral Deformation
Domenic Rosati, Sebastian Dionicio, Xijie Zeng, Subhabrata Majumdar, Frank Rudzicz, Hassan Sajjad
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Reproducibility: The New Frontier in AI Governance
Israel Mason-Williams, Gabryel Mason-Williams
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Fallacies of Data Transparency: Rethinking Nutrition Facts for AI
Judy Hanwen Shen, Ken Liu, Angelina Wang, Sarah H. Cen, Andy K Zhang, Caroline Meinhardt, Daniel Zhang, Kevin Klyman, Rishi Bommasani, Daniel E. Ho
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Robust ML Auditing using Prior Knowledge
Jade Garcia Bourrée, Augustin Godinot, Martijn De Vos, Milos Vujasinovic, Sayan Biswas, Gilles Tredan, Erwan Le Merrer, Anne-Marie Kermarrec
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
A Blueprint for a Secure EU AI Audit Ecosystem
Alejandro Tlaie
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments
Christoph Schnabl, Daniel Hugenroth, Bill Marino, Alastair R. Beresford
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Practical Principles for AI Cost and Compute Accounting
Stephen Casper, Luke Bailey, Tim Schreier
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
Chhavi Yadav, Evan Laufer, Dan Boneh, Kamalika Chaudhuri
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Methodological Challenges in Agentic Evaluations of AI Systems
Kevin Wei, Stephen Guth, Gabriel Wu, Patricia Paskov
- Published: 05 Jun 2025, Last Modified: 25 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone