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

180359539718 · Jun 202019922001200920182026
48 results for input space manipulation

New model improves neural network robustness against input manipulations.

problem Improving neural network robustness against input manipulations.
method Causal view and deep causal manipulation augmented model (deep CAMA) with data augmentation and test-time fine-tuning.
result Deep CAMA shows superior robustness against unseen manipulations compared to traditional models.

Noise added to deep Q-networks reduces adversarial attacks.

problem Vulnerability of deep reinforcement learning to policy manipulation attacks.
method Addition of noise to the parameter space of deep reinforcement learners during training.
result Noise reduces the transferability of adversarial examples.

Many problems in image processing and computer vision (e.g. colorization, style transfer) can be posed as 'manipulating' an input image into a corresponding output image given a user-specified guiding signal. A holy-grail solution towards generic image manipulation should be able to efficiently alter an input image wit…

2017-03-21abs ↗pdf ↗

Paper addresses hypothesis space misspecification in learning from human demonstrations and corrections.

problem Hypothesis space misspecification in learning from human demonstrations and corrections.
method Reason explicitly about how well the robot can explain human inputs given its hypothesis space.
result Demonstrates method on a 7 DOF robot manipulator.

Manipulated explanations can be made imperceptible to the naked eye.

problem The trustworthiness and interpretability of neural networks can be compromised by manipulable explanations.
method The paper demonstrates that explanations can be altered by applying small, imperceptible input changes that do not affect the network's output.
result An upper bound on the susceptibility of explanations to manipulation has been derived, and effective mechanisms to enhance explanation robustness have been proposed.

This work proposes a RL approach to learn versatile robotic manipulation tasks.

problem Challenging manipulation tasks in robotics and vision.
method Reinforcement learning (RL) to combine primitive skills, no intermediate rewards, few demonstrations, and efficient skill learning.
result Versatile robotic manipulation in challenging settings with temporary occlusions and dynamic scene changes.

Adversarial attacks can fool algorithmic trading systems.

problem Adversarial perturbations can manipulate algorithmic trading models.
method Real-time adversarial attacks on trading algorithms using universal perturbations.
result Perturbations can fool trading algorithms at unseen data points.

Paper discovers and manipulates artistic styles in paintings without supervision.

problem Automatic discovery and manipulation of artistic styles in large art collections.
method Unsupervised learning using archetypal analysis on deep image representations.
result Learned dictionary of archetypal styles can be used for style interpretation and manipulation.

Adversaries manipulate wireless power allocation to reduce user rates.

problem Adversaries exploit deep learning for power control to decrease communication rates.
method Adversaries craft perturbations to inputs of a DNN to minimize power allocation.
result Adversarial attacks are highly effective and robust to uncertainties.

The method learns disentangled representations for localized image manipulations.

problem Image generating neural networks are viewed as black boxes with global effects.
method Localized ResNet Autoencoder with multiple loss functions.
result The network can transfer specific facial attributes like shape and color of eyes, hair, mouth, etc. between persons.

A new method for disentangled latent spaces in VAEs that can manipulate attributes.

problem Disentangled representation of attributes in latent spaces of VAEs.
method Attribute-based regularization loss to enforce monotonic relationships between attributes and latent codes.
result Manipulation of attributes in latent spaces post-training.

We propose a mathematical model for the word-of-mouth communications among stock investors through social networks and explore how the changes of the investors' social networks influence the stock price dynamics and vice versa. An investor is modeled as a Gaussian fuzzy set (a fuzzy opinion) with the center and standar…

2016-02-19abs ↗pdf ↗

This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.

problem Solving long-horizon, complex sequential tasks in robotics with sparse rewards.
method Extends hindsight relabelling to task-specific goal distributions using a small set of demonstrations.
result Significantly higher overall performance on complex robotic manipulation tasks.

Camera stickers can fool deep learning systems by manipulating the lens, achieving 49.6% misclassification rate.

problem The vulnerability of deep learning systems to physical adversarial attacks.
method Iterative procedure to update attack perturbation and threat model for physical realizability.
result Achieved 49.6% misclassification rate for targeted attacks on ImageNet classifiers.

The paper examines how social inequality affects algorithmic classification outcomes.

problem Social inequality impacts algorithmic classification outcomes.
method Adapting models of strategic manipulation to account for social inequality and subsidy effects.
result Subsidizing disadvantaged groups can paradoxically harm both groups and the learner.

Workshop reviews techniques to understand neural NLP models.

problem Understanding the inner workings of neural networks in natural language processing.
method Systematic manipulation of inputs, decoding intermediate representations, modifying architectures, and testing on simplified languages.
result Various techniques can improve explainability of neural network models.

Paper tackles multi-object reinforcement learning, improving skill extrapolation.

problem Learning robust manipulation tasks in multi-object settings.
method Introduces a linear relation network module to enhance skill generalization.
result Agents can extrapolate and generalize to any new object number, scaling linearly.

New research shows input-gradients can be manipulated without changing model's core function, challenging their use for model interpretation.

problem Current methods for model interpretability using input-gradients are flawed due to their arbitrary manipulability.
method Investigated by reinterpreting logits as unnormalized log-densities, proposing novel approximations for score-matching.
result Improving alignment between implicit density model and data distribution enhances gradient structure and explanatory power.

New method uses explicit human demonstrations to teach missing features in reward learning.

problem Reward learning methods rely on handcrafted features, limiting their ability to adapt to new or unexplained corrections.
method Introduces human input guiding the robot from states with missing features to states without, teaching the feature explicitly and integrating it into the reward function.
result Decreases sample complexity and improves generalization of the learned reward over deep IRL baseline.

A new method improves target selection for manipulating complex systems like the brain.

problem Improper incorporation of low-variance outcomes into latent space of predictive models.
method Developed a novel objective based on supervised variational autoencoders (SVAEs) for PPCA (Probabilistic Principal Component Analysis).
result gPCR (Generative Principal Component Regression) dramatically improves target selection in manipulation compared to standard PCR and SVAEs.

This work tackles force control for contact-rich manipulation tasks with rigid robots using RL.

problem Challenges in working with real robotic hardware, especially position-controlled robots.
method Combines RL with traditional force control techniques, implementing parallel position/force control and admittance control.
result Validated methods on both simulation and real robot (UR3 e-series) for force control.

Graph neural networks are vulnerable to adversarial attacks by manipulating graph structure.

problem Vulnerability of Graph Neural Networks to adversarial attacks.
method Categorization and review of existing attacks and defenses.
result Developed a repository for empirical studies on graph adversarial attacks and defenses.

Paper analyzes robustness of non-Lipschitz networks, proving powerful adversarial attacks but offering solutions.

problem Adversarial attacks on deep networks, especially non-Lipschitz networks.
method Developed an attack model that abstracts the challenge of adversarial robustness, proving the power of such attacks and offering solutions.
result Proves powerful adversarial attacks on non-Lipschitz networks but offers solutions with abstention.

A novel RL approach learns robotic manipulation without human demonstrations.

problem Learning robotic manipulation policies efficiently and effectively.
method Introducing simulated locomotion demonstration rewards (SLDRs) to enable RL learning.
result The approach achieves higher success rates and faster learning compared to alternatives.

The paper formalizes how concepts are encoded in text-guided generative models and provides a method to manipulate them.

problem Encoding and manipulating concepts in text-guided generative models.
method Formalizing concepts as subspaces of a representation space, developing algebraic manipulation methods.
result The ability to manipulate concepts in generative models through algebraic operations on the representation.

We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers…

2016-03-23abs ↗pdf ↗

This research analyzes how input and output layers affect deep neural networks' resistance to adversarial attacks.

problem The vulnerability of deep neural networks to adversarial inputs, especially non-gradient based attacks.
method Analysis of three different fully connected dense network classes with manipulated input and output layers.
result Manipulating input and output layers can significantly enhance a deep neural network's robustness against adversarial attacks.

Concept bottleneck models enable concept manipulation for model interpretation.

problem Training models to directly predict labels without intermediate concepts.
method Train models to predict intermediate concepts at training time, then use these concepts to predict labels.
result Concept bottleneck models achieve competitive accuracy with standard models while enabling concept manipulation.

In this paper, we consider the streaming memory-limited matrix completion problem when the observed entries are noisy versions of a small random fraction of the original entries. We are interested in scenarios where the matrix size is very large so the matrix is very hard to store and manipulate. Here, columns of the o…

2015-04-13abs ↗pdf ↗