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.

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

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

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

Deep Learning Cloud Service for Black-Box Adversarial Attacks

Distributed Black-Box attacks against Image Classification.

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

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

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

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

Distributed Black-Box Attacks against Image Classification.

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

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

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

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

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

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

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

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