arXiv research

EI-MTD defends edge intelligence against adversarial attacks with dynamic scheduling.

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global …

Dynamic defense against Byzantine poisoning in federated learning.

Robust RL improves controller robustness to dynamics variations using adversarial populations.

Generative models for complex stochastic dynamics using adversarial learning.

Improves adversarial robustness of DEQ models by regulating neural dynamics.

The paper tackles adversarial attacks on recurrent neural networks.

Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.

Study on adversarial training dynamics in high dimensions using SGD.

LOGAN optimizes GAN training by improving adversarial dynamics.

New algorithm achieves both static and dynamic regret optimally against an oblivious adversary for deterministic losses.

Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers - a) harder to evade, b) easier to detect changes in the data distribution over time, and c) be ab…

Study analyzes adversarial training dynamics without data distribution assumptions.

Paper analyzes adversarial dynamics in neural networks.

New method controls linear systems with adversarial disturbances.

We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives. We train a reinforcement learning agent to sequentially acquire a subset of the information while balancing accuracy and fairness …

Paper proposes a new method to attack Bayesian forecasting models.

A method to minimize regret in multi-agent control systems with adversarial disturbances.

New controller reduces regret in non-stochastic control with adversarial perturbations.

Optimistic pricing algorithm handles online dynamic pricing with censored demand.

This work addresses dynamic KDE data structures with robustness to adversarial queries.

I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do harm and be hard to detect. This view encompasses many types of adversarial machine learning, includi…

Adversarial training leads to clean data generalization with significant robust overfitting gap.

We describe an approximate dynamic programming (ADP) approach to compute approximations of the optimal strategies and of the minimal losses that can be guaranteed in discounted repeated games with vector-valued losses. Such games prominently arise in the analysis of regret in repeated decision-making in adversarial env…

EBMs trained with ML are shown to behave like GANs with a self-adversarial loss.

New model explains GAN training dynamics and mode collapse.

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise). The objective we consider is one of regret: we desire an online control procedure that can do nearly as well as that of a procedure that has full knowledge of the disturbances in hindsight. Our main result…

New method controls linear systems with partial info and disturbances.

New algorithm reduces dynamic regret for MDPs with unknown transition and adversarial rewards.

RoGAT enhances GAT robustness against adversarial attacks.

This paper examines how adversarial perturbations affect model performance and equilibrium learning.

New bounds show complexity of adversarial decision making.

StealthRank subtly boosts LLM rankings without detectable anomalies.

We propose to incorporate adversarial dropout in generative multi-adversarial networks, by omitting or dropping out, the feedback of each discriminator in the framework with some probability at the end of each batch. Our approach forces the single generator not to constrain its output to satisfy a single discriminator,…

Generative adversarial network for probabilistic forecasting of random systems.

New algorithms improve contextual search in the presence of adversarial corruptions.

New RL method improves robustness across various conditions.

Fault detection problem for closed loop uncertain dynamical systems, is investigated in this paper, using different deep learning based methods. Traditional classifier based method does not perform well, because of the inherent difficulty of detecting system level faults for closed loop dynamical system. Specifically, …

Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and deploying this method - expensive in terms of extra memory and computation costs; …

We consider a non-stochastic online learning approach to price financial options by modeling the market dynamic as a repeated game between the nature (adversary) and the investor. We demonstrate that such framework yields analogous structure as the Black-Scholes model, the widely popular option pricing model in stochas…

New method learns population dynamics from snapshots using JKO scheme and inverse optimization.

This paper addresses tracking of a moving target in a multi-agent network. The target follows a linear dynamics corrupted by an adversarial noise, i.e., the noise is not generated from a statistical distribution. The location of the target at each time induces a global time-varying loss function, and the global loss is…

Existing approaches to online convex optimization (OCO) make sequential one-slot-ahead decisions, which lead to (possibly adversarial) losses that drive subsequent decision iterates. Their performance is evaluated by the so-called regret that measures the difference of losses between the online solution and the best ye…

Paper explains adversarial training's robust overfitting through a minimax game perspective.

New method stabilizes GAN training by solving ODEs.

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmen…

Adversarial RL recovers agent rewards from financial market data simulations.

Tackles dynamic subsurface flow via GAN with physical theory constraints.