NeurIPS 2025 Workshop RegML Submissions

Perspective: Lessons from Cybersecurity for Biological AI Safety and Regulation
Azmine Toushik Wasi, Mst Rafia Islam
- Published: 23 Sept 2025, Last Modified: 25 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
StealthEval: A Probe-Rewrite-Evaluate Workflow for Reliable Benchmarks
Lang Xiong, Nishant Bhargava, Jeremy Chang, Jianhang Hong, Haihao Liu, Kevin Zhu
- Published: 23 Sept 2025, Last Modified: 09 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Statutory Construction and Interpretation for Artificial Intelligence
Luxi He, Nimra Nadeem, Michel Liao, Howard Chen, Danqi Chen, Peter Henderson
- Published: 23 Sept 2025, Last Modified: 28 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Scratchpad Thinking: Alternation Between Storage and Computation in Latent Reasoning Models
Sayam Goyal, Brad Peters, María Emilia Granda, Akshath Vijayakumar Narmadha, Dharunish Yugeswardeenoo, Callum Stuart McDougall, Sean O'Brien, Ashwinee Panda, Kevin Zhu, Cole Blondin
- Published: 23 Sept 2025, Last Modified: 09 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
The Backfiring Effect of Weak AI Safety Regulation
Benjamin Laufer, Jon Kleinberg, Hoda Heidari
- Published: 23 Sept 2025, Last Modified: 09 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents
Gauri Kholkar, Ratinder Paul Singh Ahuja
- Published: 23 Sept 2025, Last Modified: 25 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Data Forging Attacks on Cryptographic Model Certification
Carter Luck, Olive Franzese, Elisaweta Masserova, Akira Takahashi, Antigoni Polychroniadou
- Published: 23 Sept 2025, Last Modified: 27 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
Wesley Deng, Sunnie S. Y. Kim, Akshita Jha, Ken Holstein, Motahhare Eslami, Lauren Wilcox, Leon Alexander Gatys
- Published: 23 Sept 2025, Last Modified: 09 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learning
Alexander Bakarsky, Dimitar Iliev Dimitrov, Maximilian Baader, Martin Vechev
- Published: 23 Sept 2025, Last Modified: 25 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning
Benjamin Liu, Dillon Mehta, Rishi Malhotra, Adam Zobian, Yong Ying Tan, Samir Chopra, Daniella Rand, Natalie Pang, Abhiram Gudimella, Raghav Thallapragada, Derek Jiu, Kevin Zhu
- Published: 23 Sept 2025, Last Modified: 09 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Inducing Uncertainty on Open-Weight Models for Test-Time Privacy in Image Recognition
Muhammad H. Ashiq, Peter Triantafillou, Hung Yun Tseng, Grigorios Chrysos
- Published: 23 Sept 2025, Last Modified: 19 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law
Ilija Lichkovski, Alexander Müller, Mariam Ibrahim, Tiwai Mhundwa
- Published: 23 Sept 2025, Last Modified: 23 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
The Hidden Cost of Modeling $P(X)$: Membership Inference Attacks in Generative Text Classifiers
Owais Makroo, Karan Gupta, Siva Rajesh Kasa, Sumegh Roychowdhury, Pattisapu Nikhil Priyatam, SANTHOSH KUMAR KASA, Sumit Negi
- Published: 23 Sept 2025, Last Modified: 09 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
HashMark: Watermarking Tabular/Synthetic Data For Machine Learning Via Cryptographic Hash Functions
Harish Karthikeyan, Leo de Castro, Antigoni Polychroniadou
- Published: 23 Sept 2025, Last Modified: 22 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration
Harish Karthikeyan, Yue Guo, Udari Madhushani Sehwag, Leo de Castro, Antigoni Polychroniadou, Leo Ardon, Sumitra Ganesh
- Published: 23 Sept 2025, Last Modified: 31 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
SemScore: Practical Explainable AI through Quantitative Methods to Measure Semantic Spuriosity
Jovin Leong, Wei May Chen, Tiong Kai Tan
- Published: 23 Sept 2025, Last Modified: 23 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
Vamshi Krishna Bonagiri, Ponnurangam Kumaraguru, Khanh Xuan Nguyen, Benjamin Plaut
- Published: 23 Sept 2025, Last Modified: 23 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Explanation-Driven Counterfactual Testing for Faithfulness in Vision-Language Model Explanations
Sihao Ding, Santosh Vasa, Aditi Ramadwar
- Published: 23 Sept 2025, Last Modified: 09 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
The Model Openness Framework: Promoting Completeness and Openness for Reproducibility, Transparency, and Usability in Artificial Intelligence
Matt White, Cailean Osborne, Xiao-Yang Liu, Keyi Wang, Sachin Mathew Varghese
- Published: 23 Sept 2025, Last Modified: 23 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
Sepideh Abedini, Shubhankar Mohapatra, D. B. Emerson, Masoumeh Shafieinejad, Jesse C. Cresswell, Xi He
- Published: 23 Sept 2025, Last Modified: 21 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Deepfakes in Political Manipulation: Evaluating Risks Under the AI Act
Mst Rafia Islam, Azmine Toushik Wasi
- Published: 23 Sept 2025, Last Modified: 25 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
On the Regulatory Potential of User Interfaces for AI Agent Governance
Kevin Feng, Tae Soo Kim, Rock Yuren Pang, Faria Huq, Tal August, Amy X Zhang
- Published: 23 Sept 2025, Last Modified: 09 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Debugging Concept Bottleneck Models through Removal and Retraining
Eric Enouen, sainyam galhotra
- Published: 23 Sept 2025, Last Modified: 21 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
Auditable AI Literacy Interventions: Embedding Regulatory Principles into Higher Education
Edisy Kin Wai Chan, Beatrice Yan-yan Dang
- Published: 23 Sept 2025, Last Modified: 22 Oct 2025
- RegML 2025 Poster
- Readers: Everyone
SpecEval: Evaluating Model Adherence to Behavior Specifications
Ahmed M Ahmed, Kevin Klyman, Yi Zeng, Sanmi Koyejo, Percy Liang
- Published: 23 Sept 2025, Last Modified: 23 Oct 2025
- RegML 2025 Poster
- Readers: Everyone