相关论文: Game-Theoretic Unlearnable Example Generator

We study data poisoning attacks in the online setting where training items arrive sequentially, and the attacker may perturb the current item to manipulate online learning. Importantly, the attacker has no knowledge of future training items…

In this paper we use game theory to model poisoning attack scenarios. We prove the non-existence of pure strategy Nash Equilibrium in the attacker and defender game. We then propose a mixed extension of our game model and an algorithm to…

The present survey aims at presenting the current machine learning techniques employed in security games domains. Specifically, we focused on papers and works developed by the Teamcore of University of Southern California, which deepened…

Games are natural models for multi-agent machine learning settings, such as generative adversarial networks (GANs). The desirable outcomes from algorithmic interactions in these games are encoded as game theoretic equilibrium concepts, e.g.…

Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference or can be identified during the validation phase. Therefore,…

Deception plays a critical role in many interactions in communication and network security. Game-theoretic models called "cheap talk signaling games" capture the dynamic and information asymmetric nature of deceptive interactions. But…

Existing methods for learning Stackelberg equilibria typically assume that the followers' (variational, generalized) Nash equilibrium is unique. However, in the presence of multiple equilibria, without a selection convention, the problem…

We propose a model for games in which the players have shared access to a blockchain that allows them to deploy smart contracts to act on their behalf. This changes fundamental game-theoretic assumptions about rationality since a contract…

Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model…

We study Stackelberg games where a principal repeatedly interacts with a non-myopic long-lived agent, without knowing the agent's payoff function. Although learning in Stackelberg games is well-understood when the agent is myopic, dealing…

We initiate the study of structured Stackelberg games, a novel form of strategic interaction between a leader and a follower where contextual information can be predictive of the follower's (unknown) type. Motivated by applications such as…

Many autonomous agents, such as intelligent vehicles, are inherently required to interact with one another. Game theory provides a natural mathematical tool for robot motion planning in such interactive settings. However, tractable…

We consider the problem of learning to exploit learning algorithms through repeated interactions in games. Specifically, we focus on the case of repeated two player, finite-action games, in which an optimizer aims to steer a no-regret…

Toxicity text detectors can be vulnerable to adversarial examples - small perturbations to input text that fool the systems into wrong detection. Existing attack algorithms are time-consuming and often produce invalid or ambiguous…

Generative adversarial networks (GANs) are a class of generative models, known for producing accurate samples. The key feature of GANs is that there are two antagonistic neural networks: the generator and the discriminator. The main…

Deep neural networks have been shown to be vulnerable to adversarial examples deliberately constructed to misclassify victim models. As most adversarial examples have restricted their perturbations to $L_{p}$-norm, existing defense methods…

The Stackelberg game model, where a leader commits to a strategy and the follower best responds, has found widespread application, particularly to security problems. In the security setting, the goal is for the leader to compute an optimal…

We consider the problem of training generative models with a Generative Adversarial Network (GAN). Although GANs can accurately model complex distributions, they are known to be difficult to train due to instabilities caused by a difficult…

Generative adversarial networks (GANs) represent a zero-sum game between two machine players, a generator and a discriminator, designed to learn the distribution of data. While GANs have achieved state-of-the-art performance in several…