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

October 12, 2023

October 10, 2023

October 9, 2023

October 8, 2023

Adversarial Attacks on Combinatorial Multi-Armed Bandits
Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli, Huazheng Wang, Qingyun Wu, Haoyu Zhao
Adversarial Attack Multi Armed Bandit Combinatorial Approach Combinatorial Multi Armed Bandit Bandit Instance Reward Poisoning Attack

October 7, 2023

October 6, 2023

October 4, 2023

Adversarial Attack

Papers

Fed-Safe: Securing Federated Learning in Healthcare Against Adversarial Attacks

Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks

Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks

A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks

Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach

Exploring adversarial attacks in federated learning for medical imaging

PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization

AdvSV: An Over-the-Air Adversarial Attack Dataset for Speaker Verification

An Initial Investigation of Neural Replay Simulator for Over-the-Air Adversarial Perturbations to Automatic Speaker Verification

GReAT: A Graph Regularized Adversarial Training Method

Adversarial Attacks on Combinatorial Multi-Armed Bandits

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Assessing Robustness via Score-Based Adversarial Image Generation

Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification

Improving classifier decision boundaries using nearest neighbors

Targeted Adversarial Attacks on Generalizable Neural Radiance Fields

Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System

Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors

Optimizing Key-Selection for Face-based One-Time Biometrics via Morphing