arXiv subjects

Doohyun Kim

Publications and source records attributed to Doohyun Kim.

7 recordsLinked to original sources

arXiv2026

SPOILER: TEE-Shielded DNN Partitioning of On-Device Secure Inference with Poison Learning

Deploying deep neural networks (DNNs) on edge devices exposes valuable intellectual property to model-stealing attacks. While TEE-shielded DNN partitioning (TSDP) mitigates this by isolating sensitive computations, existing paradigms fail to simultaneously satisfy privacy and efficiency. The training-before-partition paradigm suffers from intrinsic privacy leakage, whereas the partition-before-training paradigm incurs severe latency due to structural dependencies that hinder parallel execution. To overcome these limitations, we propose SPOILER, a novel search-before-training framework that fundamentally decouples the TEE sub-network from the backbone via hardware-aware neural architecture search (NAS). SPOILER identifies a lightweight TEE architecture strictly optimized for hardware constraints, maximizing parallel efficiency. Furthermore, we introduce self-poisoning learning to enforce logical isolation, rendering the exposed backbone functionally incoherent without the TEE component. Extensive experiments on CNNs and Transformers demonstrate that SPOILER achieves state-of-the-art trade-offs between security, latency, and accuracy.

cs.CR↗

arXiv2026

Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddings

The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via embedding inversion attacks. Existing paradigms face a fundamental trade-off: optimization-based methods require computationally prohibitive queries, while alignment-based approaches hinge on the unrealistic assumption of accessible in-domain training data. These constraints render them ineffective in strict black-box and cross-domain settings. To dismantle these barriers, we introduce Zero2Text, a novel training-free framework based on recursive online alignment. Unlike methods relying on static datasets, Zero2Text synergizes LLM priors with a dynamic ridge regression mechanism to iteratively align generation to the target embedding on-the-fly. We further demonstrate that standard defenses, such as differential privacy, fail to effectively mitigate this adaptive threat. Extensive experiments across diverse benchmarks validate Zero2Text; notably, on MS MARCO against the OpenAI victim model, it achieves 1.8x higher ROUGE-L and 6.4x higher BLEU-2 scores compared to baselines, recovering sentences from unknown domains without a single leaked data pair.

cs.CL↗

arXiv2025

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation

State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-timestep processing, rendering them infeasible for practical real-time applications. This inefficiency stems from their design as direct extensions of ANN paradigms, which fail to exploit key SNN properties. In this paper, we propose the timestep-compressed attack (TCA), a novel framework that significantly reduces attack latency. TCA introduces two components founded on key insights into SNN behavior. First, timestep-level backpropagation (TLBP) is based on our finding that global temporal information in backpropagation to generate perturbations is not critical for an attack's success, enabling per-timestep evaluation for early stopping. Second, adversarial membrane potential reuse (A-MPR) is motivated by the observation that initial timesteps are inefficiently spent accumulating membrane potential, a warm-up phase that can be pre-calculated and reused. Our experiments on VGG-11 and ResNet-17 with the CIFAR-10/100 and CIFAR10-DVS datasets show that TCA significantly reduces the required attack latency by up to 56.6% and 57.1% compared to SOTA methods in white-box and black-box settings, respectively, while maintaining a comparable attack success rate.

cs.CV↗

arXiv2025

STAS: Spatio-Temporal Adaptive Computation Time for Spiking Transformers

Spiking neural networks (SNNs) offer energy efficiency over artificial neural networks (ANNs) but suffer from high latency and computational overhead due to their multi-timestep operational nature. While various dynamic computation methods have been developed to mitigate this by targeting spatial, temporal, or architecture-specific redundancies, they remain fragmented. While the principles of adaptive computation time (ACT) offer a robust foundation for a unified approach, its application to SNN-based vision Transformers (ViTs) is hindered by two core issues: the violation of its temporal similarity prerequisite and a static architecture fundamentally unsuited for its principles. To address these challenges, we propose STAS (Spatio-Temporal Adaptive computation time for Spiking transformers), a framework that co-designs the static architecture and dynamic computation policy. STAS introduces an integrated spike patch splitting (I-SPS) module to establish temporal stability by creating a unified input representation, thereby solving the architectural problem of temporal dissimilarity. This stability, in turn, allows our adaptive spiking self-attention (A-SSA) module to perform two-dimensional token pruning across both spatial and temporal axes. Implemented on spiking Transformer architectures and validated on CIFAR-10, CIFAR-100, and ImageNet, STAS reduces energy consumption by up to 45.9%, 43.8%, and 30.1%, respectively, while simultaneously improving accuracy over SOTA models.

cs.LG↗

arXiv2020

On sparse identification of complex dynamical systems: A study on discovering influential reactions in chemical reaction networks

A wide variety of real life complex networks are prohibitively large for modeling, analysis and control. Understanding the structure and dynamics of such networks entails creating a smaller representative network that preserves its relevant topological and dynamical properties. While modern machine learning methods have enabled identification of governing laws for complex dynamical systems, their inability to produce white-box models with sufficient physical interpretation renders such methods undesirable to domain experts. In this paper, we introduce a hybrid black-box, white-box approach for the sparse identification of the governing laws for complex, highly coupled dynamical systems with particular emphasis on finding the influential reactions in chemical reaction networks for combustion applications, using a data-driven sparse-learning technique. The proposed approach identifies a set of influential reactions using species concentrations and reaction rates,with minimal computational cost without requiring additional data or simulations. The new approach is applied to analyze the combustion chemistry of H2 and C3H8 in a constant-volume homogeneous reactor. The influential reactions determined by the sparse-learning method are consistent with the current kinetics knowledge of chemical mechanisms. Additionally, we show that a reduced version of the parent mechanism can be generated as a combination of the significantly reduced influential reactions identified at different times and conditions and that for both H2 and C3H8 fuel, the reduced mechanisms perform closely to the parent mechanisms as a function of the ignition delay time over a wide range of conditions. Our results demonstrate the potential of the sparse-learning approach as an effective and efficient tool for dynamical system analysis and reduction. The uniqueness of this approach as applied to combustion systems lies in the ability to identify influential reactions in specified conditions and times during the evolution of the combustion process. This ability is of great interest to understand chemical reaction systems.

physics.chem-ph↗

arXiv2017

Spatial Dependence of Polycyclic Aromatic Compounds Growth in Counterflow Flames

The formation mechanisms of aromatic compounds in flame are strongly influenced by the chemical and thermal history that leads to their formation. Indeed, the complex environments that characterize combustion systems do not only affect the composition of gas-phase species, but they also determine the structure and the characteristics of the soot precursors generated. To illustrate the importance of these effects, in this work we investigate the growth mechanisms of soot precursors in an atmospheric-pressure ethylene/oxygen/argon counterflow diffusion flame, using a combination of computational and experimental techniques. In diffusion flames, flow characteristics play an important role in the formation, growth, and oxidation of particles, and soot precursors are strongly affected by the flame location. Fluid dynamics simulations and stochastic discrete modeling were employed together to identify key reaction pathways along various flow streamlines. The models were validated with experimental mass spectra obtained using aerosol mass spectrometry coupled with vacuum-ultraviolet photoionization. Results show that both the hydrogen-abstraction-acetylene-addition mechanism and oxygen-insertion reactions are responsible for the molecular growth, and their relative importance is determined by the flame conditions along the streamlines. Oxygenated species were detected in regions of high temperature, high atomic oxygen concentration, and relatively low acetylene abundance. This study also emphasizes the need to model the counterflow flame in three dimensions to capture the spatial dependence on growth mechanisms of soot precursors.

physics.chem-ph↗

arXiv2017

A New Data-Driven Sparse-Learning Approach to Study Chemical Reaction Networks

Chemical kinetic mechanisms can be represented by sets of elementary reactions that are easily translated into mathematical terms using physicochemical relationships. The schematic representation of reactions captures the interactions between reacting species and products. Determining the minimal chemical interactions underlying the dynamic behavior of systems is a major task. In this paper, we introduce a novel approach for the identification of the influential reactions in chemical reaction networks for combustion applications, using a data-driven sparse-learning technique. The proposed approach identifies a set of influential reactions using species concentrations and reaction rates, with minimal computational cost without requiring additional data or simulations. The new approach is applied to analyze the combustion chemistry of H2 and C3H8 in a constant-volume homogeneous reactor. The influential reactions identified by the sparse-learning method are consistent with the current kinetics knowledge of chemical mechanisms. Additionally, we show that a reduced version of the parent mechanism can be generated as a combination of the influential reactions identified at different times and conditions and that for both H2 and C3H8 this reduced mechanism performs closely to the parent mechanism as a function of ignition delay over a wide range of conditions. Our results demonstrate the potential of the sparse-learning approach as an effective and efficient tool for mechanism analysis and mechanism reduction.

math.OC↗