arXiv research

Study robust learning without knowing perturbation sets, using interactions with attackers.

Massif helps interpret adversarial attacks on deep learning models.

This study explains how adversarial interaction creates non-homogeneous patterns using a pseudo-Reaction-Diffusion model.

Paper proposes a new method for predicting drug interactions using adversarial autoencoders.

Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable adversarial imitation learning algorithm in a Dyna-like framework for switching be…

Adversarial attacks have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep reinforcement learning agents. The existing methods for attacking reinforcement learning agents assume the adversary either has access to the target agent's learned paramete…

Adversarial perturbations and RIS interaction vectors improve covert communication.

The paper tackles robust policy learning in multitask contextual bandits with adversarial users.

Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks. Many efforts have been devoted to enhancing the robustness of individual networks and then constructing a straightforward ensemble…

This work analyzes how different forms of compressibility affect adversarial robustness in neural networks.

Improved regret bound for adversarial bandit convex optimisation.

Proposes a multi-view architecture for drug-target interaction prediction.

Many machine learning image classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Current adversarial methods directly alter pixel colors and evaluate against pixel norm-balls: pixel perturbations smaller than a specified magnitude, according t…

Motivated by the pursuit of a systematic computational and algorithmic understanding of Generative Adversarial Networks (GANs), we present a simple yet unified non-asymptotic local convergence theory for smooth two-player games, which subsumes several discrete-time gradient-based saddle point dynamics. The analysis rev…

GAIL is a recent successful imitation learning architecture that exploits the adversarial training procedure introduced in GANs. Albeit successful at generating behaviours similar to those demonstrated to the agent, GAIL suffers from a high sample complexity in the number of interactions it has to carry out in the envi…

Paper examines Go AI robustness against adversarial attacks.

Algorithm for decentralized competition among adaptive agents.

New algorithms for planning with adversarial changes in costs.

LOGAN optimizes GAN training by improving adversarial dynamics.

A central challenge of adversarial learning is to interpret the resulting hardened model. In this contribution, we ask how robust generalization can be visually discerned and whether a concise view of the interactions between a hardened decision map and input samples is possible. We first provide a means of visually co…

Reinforcement learning is well suited for optimizing policies of recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with the real environment, and thus are expensive in model learning. Offline evaluation methods, such as importance sampling, can alleviate s…

Deep neural networks (DNN) trained in a supervised way suffer from two known problems. First, the minima of the objective function used in learning correspond to data points (also known as rubbish examples or fooling images) that lack semantic similarity with the training data. Second, a clean input can be changed by a…

SocialInteractionGAN generates realistic human interactions from low-dimensional data.

Survey of GANs and autoencoders, addressing mode collapse and likelihood issues.

Generative Adversarial Networks simulate realistic market interactions.

Adaptive framework generates challenging adversarial scenarios for autonomous vehicles.

We identify two issues with the family of algorithms based on the Adversarial Imitation Learning framework. The first problem is implicit bias present in the reward functions used in these algorithms. While these biases might work well for some environments, they can also lead to sub-optimal behavior in others. Secondl…

Efficiently controls unknown linear systems with black-box interactions.

Study shows current metrics for audio adversarial examples are unreliable for human perception.

Introduces SM-games to analyze machine learning interactions.

Generative Adversarial Networks (GANs) have received a great deal of attention due in part to recent success in generating original, high-quality samples from visual domains. However, most current methods only allow for users to guide this image generation process through limited interactions. In this work we develop a…

Game theory helps machine learn better from adversarial queries.

AR-A3C improves A3C's robustness to noisy environments.

New framework crafts adversarial examples for neural networks.

Researchers develop PAIN to improve self-driving safety through adversarial training.

New algorithms achieve no-regret learning even with adversarial transitions and losses.

Deep RL policies are vulnerable to adversarial perturbations, but vanilla training yields more robust policies.

Despite their tremendous success in a range of domains, deep learning systems are inherently susceptible to two types of manipulations: adversarial inputs -- maliciously crafted samples that deceive target deep neural network (DNN) models, and poisoned models -- adversely forged DNNs that misbehave on pre-defined input…

Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on simpler models. In thi…

Paper optimizes learning MDPs with adversarial rewards using linear models.

Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map the autoencoder's bottleneck layer output (termed as code vectors) to different no…

This work finds mixed equilibria in zero-sum games using interacting particle dynamics.

This paper improves attacks on recommender systems by solving optimization problems more precisely.

Face recognition models can be inferred from student models, posing privacy risks.

Generative Adversarial Networks (GANs) can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene. Capturing such complex interactions between different ob…

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…

New algorithms compute robustness bounds for multiclass classification models.

We provide a bridge between generative modeling in the Machine Learning community and simulated physical processes in High Energy Particle Physics by applying a novel Generative Adversarial Network (GAN) architecture to the production of jet images -- 2D representations of energy depositions from particles interacting …