Consistency Flow Generative Adversarial Network

Consistency flow generative adversarial networks (CFGANs) and related flow-based models aim to generate realistic and diverse data samples by leveraging the power of flow-based generative models within an adversarial framework. Current research focuses on extending these models to handle stochastic environments, adversarial settings (like two-player games), and robust inference in the presence of noisy or contaminated data, employing techniques like reinforcement learning to improve adversarial robustness. These advancements have implications for various applications, including improving the robustness of machine learning systems against adversarial attacks and enhancing the performance of recommendation systems and other generative tasks.

Papers

March 20, 2024

FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs
Jinmin Li, Kuofeng Gao, Yang Bai, Jingyun Zhang, Shu-tao Xia, Yisen Wang
Large Language Model Adversarial Threat MUltimodal RObustness Consistency Flow Generative Adversarial Network

October 31, 2023

Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning
Haoyu Liu, Alec F. Diallo, Paul Patras
Adversarial Reinforcement Learning General Adversarial New Censorship Instance Global Bypass Consistency Flow Generative Adversarial Network

October 4, 2023

Expected flow networks in stochastic environments and two-player zero-sum games
Marco Jiralerspong, Bilun Sun, Danilo Vucetic, Tianyu Zhang, Yoshua Bengio, Gauthier Gidel, Nikolay Malkin
Generative Flow Network Stochastic Environment Two Player Zero Sum Adversarial Environment Flow Network Consistency Flow Generative Adversarial Network

May 22, 2022

Robust Flow-based Conformal Inference (FCI) with Statistical Guarantee
Youhui Ye, Meimei Liu, Xin Xing
Conformal Prediction Outlier Detection Statistical Guarantee Conformal Inference Consistency Flow Generative Adversarial Network

January 5, 2022

An Evaluation Study of Generative Adversarial Networks for Collaborative Filtering
Fernando Benjamín Pérez Maurera, Maurizio Ferrari Dacrema, Paolo Cremonesi
Generative Adversarial Network Collaborative Filtering Ranking Task Top N Recommendation User Profile Consistency Flow Generative Adversarial Network

Consistency Flow Generative Adversarial Network

Papers

FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs

Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning

Expected flow networks in stochastic environments and two-player zero-sum games

Robust Flow-based Conformal Inference (FCI) with Statistical Guarantee

An Evaluation Study of Generative Adversarial Networks for Collaborative Filtering