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 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

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning
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

January 31, 2024

Adversarial Quantum Machine Learning: An Information-Theoretic Generalization Analysis
Petros Georgiou, Sharu Theresa Jose, Osvaldo Simeone
Adversarial Attack Quantum Classifier Information Theoretic Generalization

January 30, 2024

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
Andy Zhou, Bo Li, Haohan Wang
Language Model Adversarial Attack Native Robustness Jailbreak Attack Adaptive Attack

Adversarial Attack

Papers

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

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning

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

On the Multi-modal Vulnerability of Diffusion Models

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

Benchmarking Transferable Adversarial Attacks

Invariance-powered Trustworthy Defense via Remove Then Restore

Adversarial Quantum Machine Learning: An Information-Theoretic Generalization Analysis

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks