3 citations · 3 across the 5 of their papers we have counts for
8 papers
CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization
Xinting Liao, Behnoosh Zamanlooy, Masoumeh Shafieinejad +4
Textual Collaborative Prompt Optimization (TCPO) extends TextGrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple clients to jointly improve prompts for…
On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
Masoumeh Shafieinejad, D. B. Emerson, Behnoosh Zamanlooy +5
Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is a rising interest in generatin…
Locally Private Sampling with Public Data
Behnoosh Zamanlooy, Mario Diaz, Shahab Asoodeh
Local differential privacy (LDP) is increasingly employed in privacy-preserving machine learning to protect user data before sharing it with an untrusted aggregator. Most LDP metho…
Machine Learning-Powered Course Allocation
Ermis Soumalias, Behnoosh Zamanlooy, Jakob Weissteiner +1
We study the course allocation problem, where universities assign course schedules to students. The current state-of-the-art mechanism, Course Match, has one major shortcoming: stu…
Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?
Anastasis Kratsios, Behnoosh Zamanlooy
We study the problem of approximating compactly-supported integrable functions while implementing their support set using feedforward neural networks. Our first main result transcr…
Universal Approximation Under Constraints is Possible with Transformers
Anastasis Kratsios, Behnoosh Zamanlooy, Tianlin Liu +1
Many practical problems need the output of a machine learning model to satisfy a set of constraints, . Nevertheless, there is no known guarantee that classical neural network ar…
Learning Sub-Patterns in Piecewise Continuous Functions
Anastasis Kratsios, Behnoosh Zamanlooy
Most stochastic gradient descent algorithms can optimize neural networks that are sub-differentiable in their parameters; however, this implies that the neural network's activation…
A Canonical Transform for Strengthening the Local -Type Universal Approximation Property
Anastasis Kratsios, Behnoosh Zamanlooy
Most -type universal approximation theorems guarantee that a given machine learning model class is dense in $L^p_μ(\mathbb{…