[NeurIPS 2025] Attention! Your Vision Language Model Could Be Maliciously Manipulated

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

[CVPR2024] MMA-Diffusion: MultiModal Attack on Diffusion Models

[CVPR 2024] Boosting Adversarial Transferability by Block Shuffle and Rotation

Revisiting Transferable Adversarial Images (TPAMI 2025)

Models and examples built with TensorFlow

[NeurIPS 2023] Rethinking the Backward Propagation for Adversarial Transferability

[NeurIPS 2023] Boosting Adversarial Transferability by Achieving Flat Local Maxima

A list of recent papers about adversarial learning

[ACM MM 2023] Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer.

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

[ICCV 2023] Structure Invariant Transformation for better Adversarial Transferability

Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/sp…

Code for Natural Language Adversarial Attacks and Defenses in Word Level

[ICDM 2022] Making Reconstruction-based Method Great Again for Video Anomaly Detection (PyTorch)

A beautiful, simple, clean, and responsive Jekyll theme for academics

[TKDE 2024, CIKM 2022] SLA²P: Self-supervised Anomaly Detection with Adversarial Perturbation.

Triangle Attack: A Query-efficient Decision-based Adversarial Attack (ECCV 2022)

Robust Textual Embedding against Word-level Adversarial Attacks

Detecting Textual Adversarial Examples through Randomized Substitution and Vote

Code release for ConvNeXt model

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Boosting Transferability through Enhanced Momentum

Acceptance rates for the major AI conferences

Convert images of LaTex math equations into LaTex code.

Enhancing the Transferability of Adversarial Attacks through Variance Tuning

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).