4 papers
Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing
Sadegh Majidi, Niloofar Mireshghallah, Kazem Taram
This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. LeakyLMs is the first to demons…
From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning
Amir Tahmasbi, Sadegh Majidi, Kazem Taram +1
Spatial reasoning in large language models (LLMs) has gained increasing attention due to applications in navigation and planning. Despite strong general language capabilities, LLMs…
Enigma: Application-Layer Privacy for Quantum Optimization on Untrusted Computers
Ramin Ayanzadeh, Ahmad Mousavi, Amirhossein Basareh +2
The Early Fault-Tolerant (EFT) era is emerging, where modest Quantum Error Correction (QEC) can enable quantum utility before full-scale fault tolerance. Quantum optimization is a…
Heterogeneous Memory Benchmarking Toolkit
Golsana Ghaemi, Gabriel Franco, Kazem Taram +1
This paper presents an open-source kernel-level heterogeneous memory characterization framework (MemScope) for embedded systems. MemScope enables precise characterization of the te…