Search Results for author:
Found 27 papers, 12 papers with code
Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
The planning head utilizes flow matching and a novel masked ESDF loss to minimize collision risks for generating local trajectories, and the odometry head integrates multi-sensor inputs via a transformer encoder to predict the relative pose of the robot.
Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning
Despite recent advances in graph neural networks (GNNs) for MS prediction, current approaches face two critical limitations: (1) incomplete molecular modeling due to atom-centric message-passing mechanisms that disregard bond-level topological features, and (2) prediction frameworks that lack reliable uncertainty quantification.
Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks.
Multi-Modality Representation Learning for Antibody-Antigen Interactions Prediction
While deep learning models play a crucial role in predicting antibody-antigen interactions (AAI), the scarcity of publicly available sequence-structure pairings constrains their generalization.
Test-Time Backdoor Detection for Object Detection Models
To this end, we design TRAnsformation Consistency Evaluation (TRACE), a brand-new method for detecting poisoned samples at test time in object detection.
Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization
Deep neural networks (DNNs) are susceptible to universal adversarial perturbations (UAPs).
ViDTA: Enhanced Drug-Target Affinity Prediction via Virtual Graph Nodes and Attention-based Feature Fusion
By incorporating virtual graph nodes, we seamlessly integrate local and global features of drug molecular structures, expanding the GNN's receptive field.
Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature
In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations.
PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, \ie, adversarial attacks on deep neural networks.
TrojanRobot: Physical-World Backdoor Attacks Against VLM-based Robotic Manipulation
To address this, we propose \textit{TrojanRobot}, a highly stealthy and broadly effective robotic backdoor attack in the physical world.
Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data.
DarkSAM: Fooling Segment Anything Model to Segment Nothing
In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM.
Transferable Adversarial Facial Images for Privacy Protection
To achieve this goal, we first exploit global adversarial latent search to traverse the latent space of the generative model, thereby creating natural adversarial face images with high transferability.
BadRobot: Jailbreaking Embodied LLMs in the Physical World
Embodied AI represents systems where AI is integrated into physical entities.
Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models.
MISA: Unveiling the Vulnerabilities in Split Federated Learning
This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks.
Detecting and Corrupting Convolution-based Unlearnable Examples
To evaluate the generalization of our proposed COIN, we newly design two convolution-based UEs called VUDA and HUDA to expand the scope of convolution-based UEs.
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning
In this work, we propose AdvCLIP, the first attack framework for generating downstream-agnostic adversarial examples based on cross-modal pre-trained encoders.
Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
Building on these insights, we explore the impacts of data augmentation and gradient regularization on transferability and identify that the trade-off generally exists in the various training mechanisms, thus building a comprehensive blueprint for the regulation mechanism behind transferability.
Streamlining Social Media Information Retrieval for COVID-19 Research with Deep Learning
Conclusions: This study advances public health research by implementing a novel, systematic pipeline for curating symptom lexicons from social media data.
Large Language Models Leverage External Knowledge to Extend Clinical Insight Beyond Language Boundaries
We systematically evaluate LLMs in the Chinese medical context and develop a novel in-context learning framework to enhance their performance.
Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
Deep neural networks are proven to be vulnerable to backdoor attacks.
RIS-Position and Orientation Estimation in MIMO-OFDM Systems with Practical Scatterers
A two-step positioning scheme is exploited, where the channel parameters are first acquired, and the position-related parameters are then estimated.
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples
In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes.
Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer
While deep face recognition (FR) systems have shown amazing performance in identification and verification, they also arouse privacy concerns for their excessive surveillance on users, especially for public face images widely spread on social networks.
Optimizing Privacy-Preserving Outsourced Convolutional Neural Network Predictions
This paper proposes a new scheme for privacy-preserving neural network prediction in the outsourced setting, i. e., the server cannot learn the query, (intermediate) results, and the model.
LARSEN-ELM: Selective Ensemble of Extreme Learning Machines using LARS for Blended Data
Extreme learning machine (ELM) as a neural network algorithm has shown its good performance, such as fast speed, simple structure etc, but also, weak robustness is an unavoidable defect in original ELM for blended data.
