Search Results for author:
Found 12 papers, 7 papers with code
WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks
Deepfake technology poses increasing risks such as privacy invasion and identity theft.
MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction
To address these issues, we propose MapFusion, a novel multi-modal Bird's-Eye View (BEV) feature fusion method for map construction.
MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights
Molecular representation learning plays a crucial role in various downstream tasks, such as molecular property prediction and drug design.
Moderating the Generalization of Score-based Generative Model
To fill this gap, we first examine the current 'gold standard' in Machine Unlearning (MU), i. e., re-training the model after removing the undesirable training data, and find it does not work in SGMs.
TASAR: Transfer-based Attack on Skeletal Action Recognition
The transferability of adversarial skeletal sequences enables attacks in real-world HAR scenarios, such as autonomous driving, intelligent surveillance, and human-computer interactions.
Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks
To address such concerns, numerous AI-generated Image (AIGI) Detectors have been proposed and achieved promising performance in identifying fake images.
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space
However, the research of adversarial transferability on S-HAR is largely missing.
Post-train Black-box Defense via Bayesian Boundary Correction
To this end, we propose a new post-train black-box defense framework.
Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples
Unfortunately, we find UEs provide a false sense of security, because they cannot stop unauthorized users from utilizing other unprotected data to remove the protection, by turning unlearnable data into learnable again.
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
Via BASAR, we find on-manifold adversarial samples are extremely deceitful and rather common in skeletal motions, in contrast to the common belief that adversarial samples only exist off-manifold.
Defending Black-box Skeleton-based Human Activity Classifiers
Our method is featured by full Bayesian treatments of the clean data, the adversaries and the classifier, leading to (1) a new Bayesian Energy-based formulation of robust discriminative classifiers, (2) a new adversary sampling scheme based on natural motion manifolds, and (3) a new post-train Bayesian strategy for black-box defense.
BASAR:Black-box Attack on Skeletal Action Recognition
The robustness of skeleton-based activity recognizers has been questioned recently, which shows that they are vulnerable to adversarial attacks when the full-knowledge of the recognizer is accessible to the attacker.
