Veronica Chatrath

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Varun Ursekar, Apaar Shanker, Yash Maurya, et al.

Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents

Akshay Manglik, Apaar Shanker, Kaustubh Deshpande, et al.

MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data

Masoumeh Shafieinejad, Xi He, Mahshid Alinoori, et al.

This paper describes the MIDST challenge, which evaluates how well synthetic tabular data generated by diffusion models protects privacy against membership inference attacks (MIAs)—attacks that try to determine if someone's data was used in training. The challenge developed new attack methods and tested diffusion models on both simple and complex relational data to assess whether synthetic data truly provides privacy protection as commonly assumed.