Task and Model Agnostic Adversarial Attack on Graph Neural Networks

2021-12-25 · Kartik Sharma, Samidha Verma, Sourav Medya, Arnab Bhattacharya, Sayan Ranu

Adversarial attacks on Graph Neural Networks (GNNs) reveal their security vulnerabilities, limiting their adoption in safety-critical applications. However, existing attack strategies rely on the knowledge of either the GNN model being used or the predictive task being attacked. Is this knowledge necessary? For example, a graph may be used for multiple downstream tasks unknown to a practical attacker. It is thus important to test the vulnerability of GNNs to adversarial perturbations in a model and task agnostic setting. In this work, we study this problem and show that GNNs remain vulnerable even when the downstream task and model are unknown. The proposed algorithm, TANDIS (Targeted Attack via Neighborhood DIStortion) shows that distortion of node neighborhoods is effective in drastically compromising prediction performance. Although neighborhood distortion is an NP-hard problem, TANDIS designs an effective heuristic through a novel combination of Graph Isomorphism Network with deep Q-learning. Extensive experiments on real datasets and state-of-the-art models show that, on average, TANDIS is up to 50% more effective than state-of-the-art techniques, while being more than 1000 times faster.

📄 PDF Abstract BibTeX arXiv:2112.13267

Code (1)

idea-iitd/TANDIS 공식 구현 pytorch

Tasks

Adversarial AttackQ-Learning

Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approach

2023-11-30 · Kai Li, Jingjing Zheng, Xin Yuan, Wei Ni 외

This paper proposes a novel, data-agnostic, model poisoning attack on Federated Learning (FL), by designing a new adversarial graph autoencoder (GAE)-based framework. The attack requires no knowledge of FL training data …

Federated Learning Model Poisoning

Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack

2021-03-05 · Mengting Xu, Tao Zhang, Zhongnian Li, Mingxia Liu 외

Deep learning models (with neural networks) have been widely used in challenging tasks such as computer-aided disease diagnosis based on medical images. Recent studies have shown deep diagnostic models may not be robust …

Adversarial Attack Diagnostic Multi-Label Classification MUlTI-LABEL-ClASSIFICATION

A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP

2026-06-29 · Hodaya Krakover, Meir Yossef Levi, Eyal Gofer, Guy Gilboa arxiv

Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or kn…

Adversarial Attack

Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack

2021-01-01 · ICCV 2021 10 · Weiwei Feng, Baoyuan Wu, Tianzhu Zhang, Yong Zhang 외

Modern deep neural networks are often vulnerable to adversarial examples. Most exist attack methods focus on crafting adversarial examples in the digital domain, while only limited works study physical adversarial at…

Adversarial Attack Few-Shot Learning Meta-Learning

Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling

2019-05-26 · Avishek Joey Bose, Andre Cianflone, William L. Hamilton

Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In thi…