Blackbox Attack

Blackbox attacks target machine learning models without direct access to their internal workings, aiming to manipulate model outputs through carefully crafted inputs. Current research focuses on improving the efficiency and transferability of these attacks across diverse model architectures, employing techniques like ensemble methods, Bayesian approaches, and randomized optimization strategies to reduce the number of queries needed to successfully deceive the model. This area is crucial for assessing the robustness and security of deployed machine learning systems, with implications for various applications, including autonomous vehicles, image recognition, and cloud-based services.

Papers

January 16, 2024

Machine Learning-Based Malicious Vehicle Detection for Security Threats and Attacks in Vehicle Ad-hoc Network (VANET) Communications
Thanh Nguyen Canh, Xiem HoangVan
New Attack Vehicular Ad Hoc Network Security Threat Blackbox Attack

March 25, 2023

Ensemble-based Blackbox Attacks on Dense Prediction
Zikui Cai, Yaoteng Tan, M. Salman Asif
Adversarial Attack Dense Prediction Untargeted Attack Blackbox Attack

August 13, 2022

MaskBlock: Transferable Adversarial Examples with Bayes Approach
Mingyuan Fan, Cen Chen, Ximeng Liu, Wenzhong Guo
Adversarial Attack Adversarial Example Bayesian Inference Black Box Model Blackbox Attack

August 7, 2022

Blackbox Attacks via Surrogate Ensemble Search
Zikui Cai, Chengyu Song, Srikanth Krishnamurthy, Amit Roy-Chowdhury, M. Salman Asif
Adversarial Attack QuEry Based Attack Hard Label Attack Blackbox Attack

March 3, 2022

Label-Only Model Inversion Attacks via Boundary Repulsion
Mostafa Kahla, Si Chen, Hoang Anh Just, Ruoxi Jia
Model Inversion Attack Private Training Label Only Model Inversion Attack Blackbox Attack Black Box Model Inversion Attack

December 10, 2021

RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit
Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe
Adversarial Attack Adversarial Example Decision Based Gradient Based Adversarial Blackbox Attack