Adversarial Model

Adversarial models are increasingly used to improve machine learning systems by creating challenging scenarios that expose weaknesses and drive improvements. Current research focuses on using adversarial techniques to enhance model robustness against attacks, improve fairness in predictions by mitigating biases in training data, and quantify uncertainty more accurately. These methods find applications in diverse fields, including medical image analysis, natural language processing, and anomaly detection, ultimately leading to more reliable and trustworthy AI systems. The impact is significant, as adversarial approaches are pushing the boundaries of model performance and safety across various domains.

Papers

August 12, 2024

Fooling SHAP with Output Shuffling Attacks
Jun Yuan, Aritra Dasgupta
Adversarial Attack Black Box Model Feature Attribution Attack Strategy Fusion SHAP Adversarial Model

July 24, 2024

Dataset Distribution Impacts Model Fairness: Single vs. Multi-Task Learning
Ralf Raumanns, Gerard Schouten, Josien P. W. Pluim, Veronika Cheplygina
Multi Task Learning Gender Bias Skin Lesion Single Label ResNet Based Fairness Datasets Adversarial Model

July 13, 2024

Harvesting Private Medical Images in Federated Learning Systems with Crafted Models
Shanghao Shi, Md Shahedul Haque, Abhijeet Parida, Marius George Linguraru, Y. Thomas Hou, Syed Muhammad Anwar, Wenjing Lou
Federated Learning Medical Image Secure Aggregation Privacy Inference Adversarial Model

September 15, 2023

Towards the generation of synchronized and believable non-verbal facial behaviors of a talking virtual agent
Alice Delbosc, Magalie Ochs, Nicolas Sabouret, Brian Ravenet, Stéphane Ayache
Faithful Generation Facial Expression Facial Behaviour Adversarial Model Virtual Agent

August 26, 2023

Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content
Charles O'Neill, Jack Miller, Ioana Ciuca, Yuan-Sen Ting, Thang Bui
Language Model Data Detection Harmful Content Iterative Optimization Adversarial Fine Tuning Cycle Consistent Adversarial Network Adversarial Model

July 6, 2023

Quantification of Uncertainty with Adversarial Models
Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Günter Klambauer, Sepp Hochreiter
Deep Learning Model Adversarial Example High Uncertainty Anticipation Epistemic Uncertainty Adversarial Model Predictive Uncertainty Quantification

June 1, 2023

Adversarial-Aware Deep Learning System based on a Secondary Classical Machine Learning Verification Approach
Mohammed Alkhowaiter, Hisham Kholidy, Mnassar Alyami, Abdulmajeed Alghamdi, Cliff Zou
Adversarial Attack Adversarial Search Adversarial Model

January 22, 2023

Relaxed Models for Adversarial Streaming: The Advice Model and the Bounded Interruptions Model
Menachem Sadigurschi, Moshe Shechner, Uri Stemmer
Streaming Algorithm Oblivious Adversary Adversarial Model Machine Learned Advice Interruption Detection

November 15, 2022

Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce Tasks
Jessica Y. Bo, Hen-Wei Huang, Alvin Chan, Giovanni Traverso
Data Augmentation Electrocardiogram Data Model Generalizability Adversarial Mask Data Scarce Random Augmentation Adversarial Model

November 8, 2022

ARMOR: A Model-based Framework for Improving Arbitrary Baseline Policies with Offline Data
Tengyang Xie, Mohak Bhardwaj, Nan Jiang, Ching-An Cheng
Offline Reinforcement Learning Offline Data Model Driven Adversarial Model Based Offline RL Baseline Policy

February 26, 2022

Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space
Yu Sha, Johannes Faber, Shuiping Gou, Bo Liu, Wei Li, Stefan Schramm, Horst Stoecker, Thomas Steckenreiter, Domagoj Vnucec, Nadine Wetzstein, Andreas Widl, Kai Zhou
Anomaly Detection Anomalous Sound Detection Acoustic Data Adversarial Model Cavitation Intensity Recognition

Adversarial Model

Papers

Fooling SHAP with Output Shuffling Attacks

Dataset Distribution Impacts Model Fairness: Single vs. Multi-Task Learning

Harvesting Private Medical Images in Federated Learning Systems with Crafted Models

Towards the generation of synchronized and believable non-verbal facial behaviors of a talking virtual agent

Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content

Quantification of Uncertainty with Adversarial Models

Adversarial-Aware Deep Learning System based on a Secondary Classical Machine Learning Verification Approach

Relaxed Models for Adversarial Streaming: The Advice Model and the Bounded Interruptions Model

Pretraining ECG Data with Adversarial Masking Improves Model Generalizability for Data-Scarce Tasks

ARMOR: A Model-based Framework for Improving Arbitrary Baseline Policies with Offline Data

Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space