Adversarial Method

Adversarial methods are techniques used to improve the robustness and generalization of machine learning models by introducing carefully crafted perturbations during training. Current research focuses on applying these methods to diverse areas, including image retrieval, activity recognition, and natural language processing, often employing generative adversarial networks (GANs) or gradient-based attacks and defenses. This approach is crucial for enhancing the reliability and fairness of machine learning systems in real-world applications, particularly where data distribution shifts or malicious attacks are a concern, and is driving advancements in model interpretability and security.

Papers

October 28, 2024

TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors
Adonisz Dimitriu, Tamás Michaletzky, Viktor Remeli
Adversarial Method State of the Art Detector Tractor Trailer Vehicle Adversarial Pattern TaCo MatAtlas Cendol Adversarial CAmouflage Adversarial Texture

October 22, 2024

Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods
Tsachi Blau, Moshe Kimhi, Yonatan Belinkov, Alexander Bronstein, Chaim Baskin
Large Language Model Context Learning Shot Learning Prompt Tuning Different Context Token Embeddings Adversarial Method

September 2, 2024

A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches
Kim Jinwoo
Adversarial Attack Data Augmentation Image Retrieval Adversarial Method Cross Domain Retrieval

August 6, 2024

Adversarial Domain Adaptation for Cross-user Activity Recognition Using Diffusion-based Noise-centred Learning
Xiaozhou Ye, Kevin I-Kai Wang
Domain Adaptation Activity Recognition Generative Diffusion Model Adversarial Method Adversarial Domain Adaptation Noise Robust Learning

June 28, 2024

Kolmogorov-Smirnov GAN
Maciej Falkiewicz, Naoya Takeishi, Alexandros Kalousis
Generative Model Generative Adversarial Network Adversarial Training Adversarial Method

June 3, 2024

MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering
Robert Osazuwa Ness, Katie Matton, Hayden Helm, Sheng Zhang, Junaid Bajwa, Carey E. Priebe, Eric Horvitz
Large Language Model Native Robustness Medical Question Answering Fuzz Testing Adversarial Method Medical Question Answering Benchmark

May 9, 2024

Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers
Binxiao Huang, Jason Chun Lok, Chang Liu, Ngai Wong
Backdoor Attack Backdoor Defense Adversarial Method Backdoor Poisoning Attack Trigger Design Target Class Trigger Warning

April 7, 2024

Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4
Bishwas Mandal, George Amariucai, Shuangqing Wei
Large Language Model GPT 4 Tabular Data Task Utility Privacy Utility Adversarial Method Privacy Utility Trade Adversarial Optimization

March 28, 2024

GenAI Detection Tools, Adversarial Techniques and Implications for Inclusivity in Higher Education
Mike Perkins, Jasper Roe, Binh H. Vu, Darius Postma, Don Hickerson, James McGaughran, Huy Q. Khuat
Machine Generated Future Implication Adversarial Method genAI System Text Detector Academic Integrity Assessment Scale AI Text Detector

March 27, 2024

Fact Checking Beyond Training Set
Payam Karisani, Heng Ji
Domain Adaptation Synthetic Data Adversarial Method Multi FAct Training Set

March 2, 2024

Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
Yiran Zhao, Wenyue Zheng, Tianle Cai, Xuan Long Do, Kenji Kawaguchi, Anirudh Goyal, Michael Shieh
Adversarial Prompt Prompt Optimization Adversarial Method Greedy Coordinate

February 19, 2024

An Adversarial Approach to Evaluating the Robustness of Event Identification Models
Obai Bahwal, Oliver Kosut, Lalitha Sankar
Adversarial Attack Native Robustness Event Detection Adversarial Method Event Classification Data Driven Identification

February 18, 2024

The Effectiveness of Random Forgetting for Robust Generalization
Vijaya Raghavan T Ramkumar, Bahram Zonooz, Elahe Arani
Adversarial Attack Adversarial Training Anti Forgetting Robust Generalization Adversarial Method Robust Overfitting

January 30, 2024

Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers
Lei Xu, Sarah Alnegheimish, Laure Berti-Equille, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
Adversarial Example Text Classifier Adversarial Method Level Perturbation Designing Attack

September 6, 2023

SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series
Chang George Dong, Liangwei Nathan Zheng, Weitong Chen, Wei Emma Zhang, Lin Yue
Adversarial Attack Time Series Time Series Classification Adversarial Method Swap Distance Minimization Second Ranked Logits

August 30, 2023

MDTD: A Multi Domain Trojan Detector for Deep Neural Networks
Arezoo Rajabi, Surudhi Asokraj, Fengqing Jiang, Luyao Niu, Bhaskar Ramasubramanian, Jim Ritcey, Radha Poovendran
Deep Neural Network Low Rank Tensor Adversarial Method Trojan Detection

August 19, 2023

A Comparison of Adversarial Learning Techniques for Malware Detection
Pavla Louthánová, Matouš Kozák, Martin Jureček, Mark Stamp
Adversarial Attack Adversarial Learning Consistent Comparison Malware Detection Malware Attack Adversarial Method Adversarial Malware

May 7, 2023

SynthMix: Mixing up Aligned Synthesis for Medical Cross-Modality Domain Adaptation
Xinwen Zhang, Chaoyi Zhang, Dongnan Liu, Qianbi Yu, Weidong Cai
Domain Adaptation GAN Model Synthetic Image Critical Synthesis GAN Training Segmentation Benchmark Adversarial Method

April 16, 2023

Spot The Odd One Out: Regularized Complete Cycle Consistent Anomaly Detector GAN
Zahra Dehghanian, Saeed Saravani, Maryam Amirmazlaghani, Mohammad Rahmati
Anomaly Detection Generative Adversarial SpOT Robot Adversarial Method

March 23, 2023

Semantic Image Attack for Visual Model Diagnosis
Jinqi Luo, Zhaoning Wang, Chen Henry Wu, Dong Huang, Fernando De la Torre
Adversarial Attack Adversarial Example Adversarial Method Semantic Adversarial Semantic Attack Model Based Diagnosis

Adversarial Method

Papers

TACO: Adversarial Camouflage Optimization on Trucks to Fool Object Detectors

Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods

A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches

Adversarial Domain Adaptation for Cross-user Activity Recognition Using Diffusion-based Noise-centred Learning

Kolmogorov-Smirnov GAN

MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering

Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers

Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4

GenAI Detection Tools, Adversarial Techniques and Implications for Inclusivity in Higher Education

Fact Checking Beyond Training Set

Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling

An Adversarial Approach to Evaluating the Robustness of Event Identification Models

The Effectiveness of Random Forgetting for Robust Generalization

Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers

SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series

MDTD: A Multi Domain Trojan Detector for Deep Neural Networks

A Comparison of Adversarial Learning Techniques for Malware Detection

SynthMix: Mixing up Aligned Synthesis for Medical Cross-Modality Domain Adaptation

Spot The Odd One Out: Regularized Complete Cycle Consistent Anomaly Detector GAN

Semantic Image Attack for Visual Model Diagnosis