Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

22446688 · Jun 202019922001200920182026
48 results for Hardware Reverse Engineering

Paper evaluates security of deep learning from side-channel attacks.

problem Security of deep learning algorithms from side-channel attacks.
method Uses hardware performance counters to test for information leakage in CNNs.
result Shows alarms for potential data privacy breaches in CNNs.

This paper uses machine learning to assist automation engineers in decision making.

problem Imperfect decision making by automation engineers leads to multiple iterations and increased time for software development.
method Defined challenges and proposed solutions using machine learning for automation engineering, including code classification, finding similar code snippets, and hardware selection.
result Paragraph embedding techniques achieved an F1-score of 72% for classifying automation using code snippets, and autoencoder models for hardware recommendation achieved p@3 and p@5 of 0.79 and 0.95, respectively.

Paper extends method to detect reverse engineering attacks on DNN classifiers.

problem Detecting reverse engineering attacks on deep neural network image classifiers.
method Extend ADA approach to detect RE attacks (ADA-RE).
result Successfully detects 'stealthy' RE attacks before they launch test-time evasion attacks.

We introduce a general procedure called `reverse engineering' that can be used to construct infinite families of smooth 4-manifolds in a given homeomorphism type. As one of the applications of this technique, we produce an infinite family of pairwise nondiffeomorphic 4-manifolds homeomorphic to CP^2#3(-CP^2).

2007-01-29abs ↗pdf ↗

Framework learns to optimize tensor programs for various hardware.

problem Manual optimization of tensor operators for deep learning limits applicability and increases engineering costs.
method Learning-based statistical cost models guide tensor operator implementations over billions of variants.
result Framework delivers performance competitive with hand-tuned libraries across multiple hardware targets.

Design automation optimizes deep learning models for various hardware.

problem Designing efficient deep learning models requires balancing algorithm and hardware.
method Proposes design automation techniques for specialized neural networks, including auto pruning and quantization.
result Learning-based automation achieves superior performance and efficiency compared to human design.

Reverse engineered RNNs reveal line attractor dynamics for sentiment classification.

problem Understanding how recurrent neural networks solve sequential tasks like sentiment classification.
method Dynamical systems analysis to reverse engineer trained RNNs, identifying fixed points and linearized dynamics.
result Trained RNNs converge to low-dimensional line attractor dynamics, providing interpretable solutions.

Method extracts original shapes from CAD models using clustering and implicitization.

problem Reverse engineering of geometric models from numerical representations.
method Combining clustering analysis with approximate implicitization.
result Automatic recovery of algebraic hypersurfaces of any degree in any dimension.

IReEn reveals functionality of black-box agents via iterative neural synthesis.

problem Revealing the functionality of a black-box agent without privileged information.
method Iterative refinement of candidate programs using neural program synthesis.
result The approach finds a functional equivalent program in 78% of cases, outperforming state-of-the-art.

Quantum machine learns faster by reverse annealing on AQCs.

problem Training RBMs on AQCs is hard due to low qubit connectivity.
method Embedding RBM nodes to virtual qubits, semantic quantum search, reverse annealing schedule.
result Reverse annealing accelerates RBM training and improves reconstruction scores.

GPflow is a Gaussian process library that uses TensorFlow for its core computations and Python for its front end. The distinguishing features of GPflow are that it uses variational inference as the primary approximation method, provides concise code through the use of automatic differentiation, has been engineered with…

2016-10-27abs ↗pdf ↗

New method improves convergence of gradient descent for non-convex, non-reversible Markov chains.

problem Improving convergence of gradient descent for non-convex, non-reversible Markov chains.
method Introducing a new technique that varies the mixing levels of the Markov chains to establish non-ergodic convergence under wider step sizes.
result Established non-ergodic convergence for non-convex problems and non-reversible finite-state Markov chains.

Survey of ART neural networks for engineering applications.

problem Understanding and utilizing ART neural networks for various machine learning tasks.
method Comprehensive review of classic and modern ART models, describing learning dynamics and engineering properties.
result Compilation of ART models and their properties for engineering applications.

Locally private reinforcement learning protects individual environments from reverse engineering.

problem Protecting private information in distributed reinforcement learning environments.
method Locally differentially private algorithms that protect local agents' models from adversarial reverse engineering.
result Demonstrated that the proposed algorithm performs well under local differential privacy (LDP).

BoTorch optimizes Bayesian optimization with MC methods and auto-differentiation.

problem Efficient global optimization for various applications.
method Monte-Carlo acquisition functions, sample average approximation, auto-differentiation, variance reduction.
result Improved sample efficiency compared to other libraries.

Paper reviews neuromorphic engineering features and compares analog vs digital systems.

problem Lack of consensus and unclear features in neuromorphic engineering.
method Review of recent work, comparison of machine learning accelerator chips.
result Analog processing and reduced bit precision architectures offer best efficiencies.

Unified understanding of neural networks on group operations verified.

problem Understanding and verifying neural networks trained on group operations.
method Investigated one-hidden-layer neural networks trained on binary operation of finite groups, revealing structure and providing a compact proof of model performance.
result Verified explanation applies to a large fraction of networks trained on the symmetric group S5, providing a >=95% accuracy bound for 45% of models.

We perform the first study of the tradeoff space of access methods and replication to support statistical analytics using first-order methods executed in the main memory of a Non-Uniform Memory Access (NUMA) machine. Statistical analytics systems differ from conventional SQL-analytics in the amount and types of memory …

2014-03-28abs ↗pdf ↗

We reverse engineer dynamics of financial contagion to find the scenario of smallest exogenous shock that, should it occur, would lead to a given final systemic loss. This reverse stress test can be used to identify the potential triggers of systemic events, and it removes the arbitrariness in the selection of shock sc…

2017-02-28abs ↗pdf ↗

Investigates ways to train larger models with fewer resources, finding that test loss depends only on the actual number of trainable parameters.

problem Training larger models for cheaper under hardware constraints.
method Emulates an increase in effective parameters using frozen random parameters or fast structured transforms.
result Scaling laws cannot be deceived by spurious parameters; test loss depends only on the actual number of trainable parameters.

Developing active inference agents for edge devices with limited resources.

problem Creating effective active inference agents on edge devices with limited computational resources.
method Introducing a software toolbox to accelerate the development of active inference agents by non-experts.
result Accelerates the democratization of active inference agents for edge devices.

Morph accelerates 3D CNNs for video recognition, reducing energy consumption and improving performance.

problem Efficiently accelerating 3D CNNs for video recognition is challenging due to their large memory footprint and higher dimensionality.
method Designing a flexible accelerator called Morph that adapts to different spatial and temporal tiling strategies, and codesigning a software infrastructure to control the hardware.
result Morph achieves up to 3.4x reduction in energy consumption and up to 5.1x improvement in performance/watt compared to a baseline 3D CNN accelerator.

Stealthy hardware Trojan exploits DLA architecture vulnerabilities.

problem Security of DLA deployed on hardware accelerators.
method Input Interception Attack (IIA) exploiting statistical properties of DLA outputs.
result Stealthy Trojan can trigger with some definiteness.

Ansor generates high-performance tensor programs for deep learning.

problem Generating high-performance tensor programs for deep learning on various hardware platforms is challenging.
method Ansor uses a hierarchical representation of the search space, sampling programs, and evolutionary search with a learned cost model to find high-performance programs.
result Ansor improves deep neural network execution performance up to 3.8x on Intel CPU, 2.6x on ARM CPU, and 1.7x on NVIDIA GPU.

DeepFense detects adversarial inputs in real-time for DL models.

problem Malicious attacks on autonomous DL systems in critical applications.
method Formalizes adversarial detection as an optimization problem, trains modular redundancies for validation.
result Achieves up to two orders of magnitude performance improvement with online adversarial sample detection.

PINNs help construct minimal surfaces in hyperbolic space, proving a conjecture about HOMFLY polynomial coefficients.

problem Constructing minimal surfaces in hyperbolic space asymptotic to a given knot.
method Physics-informed neural networks (PINNs) with careful engineering of model architecture and residual evaluation.
result Numerical evidence supports Joel Fine's conjecture about minimal surfaces and HOMFLY polynomial coefficients.