Adversarial Attack

Adversarial attacks aim to deceive machine learning models by subtly altering input data, causing misclassifications or other erroneous outputs. Current research focuses on developing more robust models and detection methods, exploring various attack strategies across different model architectures (including vision transformers, recurrent neural networks, and graph neural networks) and data types (images, text, signals, and tabular data). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of AI systems in diverse applications, from autonomous vehicles to medical diagnosis and cybersecurity.

Papers

February 15, 2024

Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks
Álvaro Huertas-García, Alejandro Martín, Javier Huertas-Tato, David Camacho
Language Model Adversarial Attack Adversarial Training Encoder Decoder Model Prey Camouflage Adversarial CAmouflage Decoder Only Model

February 13, 2024

Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks
Qiyuan An, Christos Sevastopoulos, Fillia Makedon
Adversarial Attack Native Robustness Adversarial Perturbation Adversarial Image Hidden Layer Traditional Adversarial Indoor Robot Navigation Free Space Segmentation

February 12, 2024

February 9, 2024

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
Enyi Jiang, Gagandeep Singh
Adversarial Attack Adversarial Training Adversarial Robustness \Ell_p$ Norm Norm Attack Robustness Trade

February 8, 2024

Reinforcement Learning as a Catalyst for Robust and Fair Federated Learning: Deciphering the Dynamics of Client Contributions
Jialuo He, Wei Chen, Xiaojin Zhang
Reinforcement Learning Adversarial Attack Deep Reinforcement Learning Native Robustness Robust Version Client Contribution Federated Reinforcement Learning FAIR Federated Learning

February 6, 2024

February 5, 2024

February 4, 2024

February 3, 2024

Evaluating the Robustness of Off-Road Autonomous Driving Segmentation against Adversarial Attacks: A Dataset-Centric analysis
Pankaj Deoli, Rohit Kumar, Axel Vierling, Karsten Berns
Adversarial Attack Autonomous Driving Native Robustness Data Perspective German Outdoor and Offroad Dataset Autonomous Off Road Driving

February 2, 2024

February 1, 2024

Tropical Decision Boundaries for Neural Networks Are Robust Against Adversarial Attacks
Kurt Pasque, Christopher Teska, Ruriko Yoshida, Keiji Miura, Jefferson Huang
Neural Network Adversarial Attack Native Robustness Decision Boundary Piecewise Linear

Adversarial Attack

Papers

Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks

Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks

Accelerated Smoothing: A Scalable Approach to Randomized Smoothing

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness

Reinforcement Learning as a Catalyst for Robust and Fair Federated Learning: Deciphering the Dynamics of Client Contributions

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons

PAC-Bayesian Adversarially Robust Generalization Bounds for Graph Neural Network

AttackNet: Enhancing Biometric Security via Tailored Convolutional Neural Network Architectures for Liveness Detection

FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution

Partially Recentralization Softmax Loss for Vision-Language Models Robustness

Generalization Properties of Adversarial Training for $\ell_0$-Bounded Adversarial Attacks

Arabic Synonym BERT-based Adversarial Examples for Text Classification

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks

DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms in Vision Transformers

Evaluating the Robustness of Off-Road Autonomous Driving Segmentation against Adversarial Attacks: A Dataset-Centric analysis

Cheating Suffix: Targeted Attack to Text-To-Image Diffusion Models with Multi-Modal Priors

SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding

STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognition

Tropical Decision Boundaries for Neural Networks Are Robust Against Adversarial Attacks