arXiv subjects

Kazem Taram

Publications and source records attributed to Kazem Taram.

4 recordsLinked to original sources

arXiv2026

Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing

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 demonstrate that key model and deployment details can be inferred using only token generation timing, even when interacting through remote APIs. LeakyLMs introduces two core attacks. The first attack targets inference optimizations and deployment strategies. For example, our attack detects whether a provider uses speculative decoding, a widely deployed inference-time optimization, and further identifies the context length of the draft model used in the pipeline. Our measurements show that Google Gemini Flash 2.5 uses speculative decoding with a draft context window of approximately 128K tokens. The second attack recovers key architectural properties, including the number of transformer layers, hidden dimension size, and number of attention heads. To achieve this, LeakyLMs builds a detailed and accurate model of token-generation timing on modern NVIDIA GPUs, characterizing how latency scales with model configuration and hardware parameters. The attack then performs a search over the architecture space using this timing model. In experiments with Llama models, the near-correct architectural configuration appears in the top-10 guesses more than 90% of the time.

cs.CR↗

arXiv2025

From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning

Spatial reasoning in large language models (LLMs) has gained increasing attention due to applications in navigation and planning. Despite strong general language capabilities, LLMs still struggle with spatial transformations and multi-step planning in structured environments. We propose a two-stage approach that decomposes spatial reasoning into atomic building blocks and their composition. First, we apply supervised fine-tuning on elementary spatial transformations, such as rotation, translation, and scaling, to equip the model with basic spatial physics. We then freeze this physics-aware model and train lightweight LoRA adapters within the GRPO framework to learn policies that compose these building blocks for multi-step planning in puzzle-based environments, in a closed-loop manner. To support this pipeline, we synthesize an ASCII-art dataset and construct a corresponding ASCII-based reinforcement learning environment. Our method consistently outperforms baselines, including the generic backbone, physics-aware model, and end-to-end RL models, under both Dynamic environments with explicit state updates and Static environments where the model must rely on its internal state across steps. In addition, the proposed approach converges faster and exhibits more stable training compared to end-to-end reinforcement learning from scratch. Finally, we analyze attention patterns to assess whether fine-tuning induces meaningful improvements in spatial understanding.

cs.AI↗

arXiv2025

Enigma: Application-Layer Privacy for Quantum Optimization on Untrusted Computers

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 leading candidate for early applications, but protecting these workloads is critical since they will run on expensive cloud services where providers could learn sensitive problem details. Experience with classical computing systems has shown that treating security as an afterthought can lead to significant vulnerabilities. Thus, we must address the security implications of quantum computing before widespread adoption. However, current Secure Quantum Computing (SQC) approaches, although theoretically promising, are impractical in the EFT era: blind quantum computing requires large-scale quantum networks, and quantum homomorphic encryption depends on full QEC. We propose application-specific SQC, a principle that applies obfuscation at the application layer to enable practical deployment while remaining agnostic to algorithms, computing models, and hardware architectures. We present Enigma, the first realization of this principle for quantum optimization. Enigma integrates three complementary obfuscations: ValueGuard scrambles coefficients, StructureCamouflage inserts decoys, and TopologyTrimmer prunes variables. These techniques guarantee recovery of original solutions, and their stochastic nature resists repository-matching attacks. Evaluated against seven state-of-the-art AI models across five representative graph families, even combined adversaries, under a conservatively strong attacker model, identify the correct problem within their top five guesses in only 4.4% of cases. The protections come at the cost of problem size and T-gate counts increasing by averages of 1.07x and 1.13x, respectively, with both obfuscation and decoding completing within seconds for large-scale problems.

quant-ph↗

arXiv2025

Heterogeneous Memory Benchmarking Toolkit

This paper presents an open-source kernel-level heterogeneous memory characterization framework (MemScope) for embedded systems. MemScope enables precise characterization of the temporal behavior of available memory modules under configurable contention stress scenarios. MemScope leverages kernel-level control over physical memory allocation, cache maintenance, CPU state, interrupts, and I/O device activity to accurately benchmark heterogeneous memory subsystems. This gives us the privilege to directly map pieces of contiguous physical memory and instantiate allocators, allowing us to finely control cores to create and eliminate interference. Additionally, we can minimize noise and interruptions, guaranteeing more consistent and precise results compared to equivalent user-space solutions. Running our Framework on a Xilinx Zynq UltraScale+ ZCU102 CPU-FPGA platform demonstrates its capability to precisely benchmark bandwidth and latency across various memory types, including PL-side DRAM and BRAM, in a multi-core system.

cs.AR↗