activity
20242026
collaborators

6 papers

cs.LG2026

Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification

Shaddin Dughmi, Mahdi Haghifam, Yusuf Hakan Kalayci

Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execut…

cs.LG2026

The Distillation Game: Adaptive Attacks & Efficient Defenses

Youssef Allouah, Mahdi Haghifam, Sanmi Koyejo +1

Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate. We study this trade-off t…

cs.LG2025

The Sample Complexity of Membership Inference and Privacy Auditing

Mahdi Haghifam, Adam Smith, Jonathan Ullman

A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a member of the training data or a…

cs.LG2025

On Traceability in Stochastic Convex Optimization

Sasha Voitovych, Mahdi Haghifam, Idan Attias +3

In this paper, we investigate the necessity of traceability for accurate learning in stochastic convex optimization (SCO) under geometries. Informally, we say a learning a…

cs.LG2024

Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization

Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam +2

In this work, we investigate the interplay between memorization and learning in the context of \emph{stochastic convex optimization} (SCO). We define memorization via the informati…

cs.LG2024

Private Geometric Median

Mahdi Haghifam, Thomas Steinke, Jonathan Ullman

In this paper, we study differentially private (DP) algorithms for computing the geometric median (GM) of a dataset: Given points, in , the goal i…