Transferable Decoding with Visual Entities for Zero-Shot Image Captioning, ICCV 2023

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

The extension of "Patch-wise Attack for Fooling Deep Neural Network (ECCV2020)", and we aim to boost the success rates of targeted attack.

Our Team (green hand) 6th Solution for CVPR-2021 AIC-VI: Unrestricted Adversarial Attacks on ImageNet

SaTML 2023, 1st place in CVPR’21 Security AI Challenger: Unrestricted Adversarial Attacks on ImageNet.

Source of the ECCV22 paper "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity"

Our simple but effective staircase sign method which boosts the transferability of both non-targeted and targeted attacks.

A Systematic Investigation of Transferability and Robustness of Humor Detection Models

(AAAI 2024) Transferable Adversarial Attacks for Object Detection using Object-Aware Significant Feature Distortion

[ICCV2023] ETran: Energy-based Transferability Estimation

Testing whether local biodiversity estimates can be robustly predicted among similar studies

Source of the UAI2022 paper "Efficient and Transferable Adversarial Examples from Bayesian Neural Networks"

Metrics to assess the generalisation ability of NILM algorithms

A list of transferability related papers

Formalizing Attacker Scenarios for Adversarial Transferability

[BMVC 2023] Diversifying the High-level Features for better Adversarial Transferability

A Transferability-guided Protein-Ligand Interaction Prediction Method

Multi-source Transfer Learning method for time series with Shapelet Similarity-based Source Selection implemented with Keras

Homework of Security and Privacy of Machine Learning (SPML Lectured by Shang-Tse Chen at NTU)

Project template for creating C software modules relying on UDP socket communications