Adversarial Detection

Adversarial detection focuses on identifying maliciously perturbed inputs—adversarial examples—that fool machine learning models, aiming to enhance the robustness and security of AI systems. Current research emphasizes developing efficient and generalizable detection methods, exploring diverse approaches such as self-supervised learning, neural codecs, and analysis of model predictions and feature attributions, often employing architectures like autoencoders, LSTMs, and diffusion models. These advancements are crucial for securing AI applications across various domains, from autonomous driving and speaker verification to face recognition and network security, mitigating the risks posed by adversarial attacks.

Papers

November 11, 2024

Adversarial Detection with a Dynamically Stable System
Xiaowei Long, Jie Lin, Xiangyuan Yang
Adversarial Example Adversarial Detection

October 30, 2024

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector
Youcheng Huang, Fengbin Zhu, Jingkun Tang, Pan Zhou, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua
Adversarial Attack Vision Language Model Adversarial Image X Vector Adversarial Detection

August 8, 2024

EdgeShield: A Universal and Efficient Edge Computing Framework for Robust AI
Duo Zhong, Bojing Li, Xiang Chen, Chenchen Liu
Adversarial Attack Real Time Edge Computing Universal Image Adversarial Detection Efficient Detection Robust AI Edge Offloading

July 5, 2024

Self-Supervised Representation Learning for Adversarial Attack Detection
Yi Li, Plamen Angelov, Neeraj Suri
Self Supervised Self Supervised Representation Learning Adversarial Detection Adversarial Attack Detection

June 7, 2024

Neural Codec-based Adversarial Sample Detection for Speaker Verification
Xuanjun Chen, Jiawei Du, Haibin Wu, Jyh-Shing Roger Jang, Hung-yi Lee
Speaker Verification Adversarial Sample Adversarial Detection Neural Codec

May 25, 2024

Detecting Adversarial Data via Perturbation Forgery
Qian Wang, Chen Li, Yuchen Luo, Hefei Ling, Ping Li, Jiazhong Chen, Shijuan Huang, Ning Yu
Adversarial Attack Adversarial Noise Adversarial Detection Adversarial Data Gradient Based Adversarial Specific Forgery

April 18, 2024

Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors
Raz Lapid, Almog Dubin, Moshe Sipper
Adversarial Detection Treasure Trove Adversarial Retraining Adaptive Adversarial Attack

April 14, 2024

FaceCat: Enhancing Face Recognition Security with a Unified Diffusion Model
Jiawei Chen, Xiao Yang, Yinpeng Dong, Hang Su, Zhaoxia Yin
Adversarial Detection Unified Generative

April 12, 2024

PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis
Dipkamal Bhusal, Md Tanvirul Alam, Monish K. Veerabhadran, Michael Clifford, Sara Rampazzi, Nidhi Rastogi
Adversarial Attack Human Prediction Adversarial Sample Feature Attribution Adversarial Detection Adversarial Attack Detection Predicate Argument Structure

November 10, 2023

Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous
Ziwei Wang, Nabil Aouf, Jose Pizarro, Christophe Honvault
Deep Learning Adversarial Attack Relative Pose Adversarial Detection Rendezvous Problem Autonomous Spacecraft Adversarial Attack Detection Relative Positional

September 5, 2023

RobustEdge: Low Power Adversarial Detection for Cloud-Edge Systems
Abhishek Moitra, Abhiroop Bhattacharjee, Youngeun Kim, Priyadarshini Panda
Adversarial Attack Adversarial DEfense Edge Cloud Adversarial Detection

August 7, 2023

Unsupervised Adversarial Detection without Extra Model: Training Loss Should Change
Chien Cheng Chyou, Hung-Ting Su, Winston H. Hsu
Adversarial Attack Full Model Adversarial Training Adversarial Robustness Cross Entropy Loss Adversarial Detection Training Loss

August 4, 2023

AdvFAS: A robust face anti-spoofing framework against adversarial examples
Jiawei Chen, Xiao Yang, Heng Yin, Mingzhi Ma, Bihui Chen, Jianteng Peng, Yandong Guo, Zhaoxia Yin, Hang Su
Adversarial Example Anti Spoofing Adversarial Detection Adversarial Defense Face Representation

June 27, 2023

On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection
Songyang Gao, Shihan Dou, Qi Zhang, Xuanjing Huang, Jin Ma, Ying Shan
Adversarial Sample Adversarial Detection Adversarial Attack Detection

June 10, 2023

Boosting Adversarial Robustness using Feature Level Stochastic Smoothing
Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan, R. Venkatesh Babu
Native Robustness Adversarial Training Adversarial Robustness Adversarial DEfense Adversarial Detection Node Aware Bi Smoothing

June 7, 2023

Adversarial Sample Detection Through Neural Network Transport Dynamics
Skander Karkar, Patrick Gallinari, Alain Rakotomamonjy
Neural Network Adversarial Sample Vector Field Adversarial Detection Invisible Attack

May 25, 2023

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score
Shuhai Zhang, Feng Liu, Jiahao Yang, Yifan Yang, Changsheng Li, Bo Han, Mingkui Tan
Adversarial Sample Additive Perturbation Adversarial Detection Adversarial Data

May 3, 2023

New Adversarial Image Detection Based on Sentiment Analysis
Yulong Wang, Tianxiang Li, Shenghong Li, Xin Yuan, Wei Ni
Adversarial Example Sentiment Analysis Adversarial Detection Adversarial Example Detection

May 2, 2023

Hamming Similarity and Graph Laplacians for Class Partitioning and Adversarial Image Detection
Huma Jamil, Yajing Liu, Turgay Caglar, Christina M. Cole, Nathaniel Blanchard, Christopher Peterson, Michael Kirby
Adversarial Image Graph Laplacian ReLU Activation Adversarial Detection Neural Network Representation Class Separation Hamming Space

April 27, 2023

Detection of Adversarial Physical Attacks in Time-Series Image Data
Ramneet Kaur, Yiannis Kantaros, Wenwen Si, James Weimer, Insup Lee
Adversarial Attack Data Detection Time Series Adversarial Noise Adversarial Detection