相关论文: An Optimal Control View of Adversarial Machine Lea…

The ever-growing big data and emerging artificial intelligence (AI) demand the use of machine learning (ML) and deep learning (DL) methods. Cybersecurity also benefits from ML and DL methods for various types of applications. These methods…

We consider data poisoning attacks, a class of adversarial attacks on machine learning where an adversary has the power to alter a small fraction of the training data in order to make the trained classifier satisfy certain objectives. While…

We frame the meta-learning of prediction procedures as a search for an optimal strategy in a two-player game. In this game, Nature selects a prior over distributions that generate labeled data consisting of features and an associated…

Classification problems in security settings are usually contemplated as confrontations in which one or more adversaries try to fool a classifier to obtain a benefit. Most approaches to such adversarial classification problems have focused…

Adversarial attacks on machine learning models often rely on small, imperceptible perturbations to mislead classifiers. Such strategy focuses on minimizing the visual perturbation for humans so they are not confused, and also maximizing the…

In this work we seek for an approach to integrate safety in the learning process that relies on a partly known state-space model of the system and regards the unknown dynamics as an additive bounded disturbance. We introduce a framework for…

Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider the problem of learning how to actively perturb a system to…

Recent advances in artificial intelligence and the increasing need for powerful defensive measures in the domain of network security, have led to the adoption of deep learning approaches for use in network intrusion detection systems. These…

Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have observed that loss gradients from adversarially trained DNNs…

We consider the problem of prediction by a machine learning algorithm, called learner, within an adversarial learning setting. The learner's task is to correctly predict the class of data passed to it as a query. However, along with queries…

Reinforcement learning can acquire complex behaviors from high-level specifications. However, defining a cost function that can be optimized effectively and encodes the correct task is challenging in practice. We explore how inverse optimal…

We study defense strategies against reward poisoning attacks in reinforcement learning. As a threat model, we consider attacks that minimally alter rewards to make the attacker's target policy uniquely optimal under the poisoned rewards,…

Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic…

The adversarial risk of a machine learning model has been widely studied. Most previous works assume that the data lies in the whole ambient space. We propose to take a new angle and take the manifold assumption into consideration. Assuming…

Deep neural networks have demonstrated their capability to learn control policies for a variety of tasks. However, these neural network-based policies have been shown to be susceptible to exploitation by adversarial agents. Therefore, there…

Reinforcement learning is one of the core components in designing an artificial intelligent system emphasizing real-time response. Reinforcement learning influences the system to take actions within an arbitrary environment either having…

We study bandit best-arm identification with arbitrary and potentially adversarial rewards. A simple random uniform learner obtains the optimal rate of error in the adversarial scenario. However, this type of strategy is suboptimal when the…

Recent works have demonstrated the vulnerability of Deep Reinforcement Learning (DRL) algorithms against training-time, backdoor poisoning attacks. The objectives of these attacks are twofold: induce pre-determined, adversarial behavior in…