black-box-attacks

max-andr/square-attack

Square Attack: a query-efficient black-box adversarial attack via random search [ECCV 2020]

kenny-co/procedural-advml

Task-agnostic universal black-box attacks on computer vision neural network via procedural noise (CCS'19)

fra31/sparse-rs

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

hmdolatabadi/AdvFlow

[NeurIPS2020] The official repository of "AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows".

fra31/sparse-imperceivable-attacks

Sparse and Imperceivable Adversarial Attacks (accepted to ICCV 2019).

TrustworthyDL/LeBA

[NeurIPS'20] Learning Black-Box Attackers with Transferable Priors and Query Feedback

HangJie720/Ensemble_Adversarial_Attack

Ensemble Adversarial Black-Box Attacks against Deep Learning Systems Trained by MNIST, USPS and GTSRB Datasets

ricvolpi/domain-shift-robustness

Code for the paper "Addressing Model Vulnerability to Distributional Shifts over Image Transformation Sets", ICCV 2019

Jack-lx-jiang/VBAD

Black-box Adversarial Attacks on Video Recognition Models. (VBAD)

qroa/QROA

QROA: A Black-Box Query-Response Optimization Attack on LLMs

qwqoro/ML-Talk

📄 [Talk] OFFZONE 2022 / ODS Data Halloween 2022: Black-box attacks on ML models + with use of open-source tools

fiveai/GFCS

Code for the ICLR 2022 paper "Attacking deep networks with surrogate-based adversarial black-box methods is easy"

wuhanstudio/blackbox-adversarial-toolbox

Distributed Black-Box Attacks against Image Classification.

wuhanstudio/DeepAPI

Deep Learning Cloud Service for Black-Box Adversarial Attacks

wi-pi/rethinking-image-scaling-attacks

[ICML 2022] Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems

wuhanstudio/adversarial-classification

Distributed Black-Box attacks against Image Classification.

AngusG/tflite-android-black-box-attacks

iamgroot42/blackboxsok

Code for 'SoK: Pitfalls in Evaluating Black-Box Attacks' , SaTML 2024.

quqixun/AdversarialAttack

Attack models that are pretrained on ImageNet. (1) Attack single model or multiple models. (2) Apply white-box attacks or black-box attacks. (3) Apply non-targeted attacks or targeted attacks.

Raghu150999/BILEAT_E2E_ABSA

BERT based deep neural network for aspect-based sentiment analysis.

acristofari/ord

Derivative-free solver for the minimization of a function over the convex hull of a set of vectors

GZHU-DVL/DMA

Code for paper "Boosting Query Effificiency of Meta Attack with Dynamic Fine-tuning"