Search Results for author:
Found 19 papers, 4 papers with code
Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers
The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video domains.
Feature Space Perturbations Yield More Transferable Adversarial Examples
Many recent works have shown that deep learning models are vulnerable to quasi-imperceptible input perturbations, yet practitioners cannot fully explain this behavior.
Transferable Perturbations of Deep Feature Distributions
Almost all current adversarial attacks of CNN classifiers rely on information derived from the output layer of the network.
Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability
We consider the blackbox transfer-based targeted adversarial attack threat model in the realm of deep neural network (DNN) image classifiers.
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
The process is hard, often requires models with large capacity, and suffers from significant loss on clean data accuracy.
Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?
During the online phase of the attack, we then leverage representations of highly related proxy classes from the whitebox distribution to fool the blackbox model into predicting the desired target class.
The Untapped Potential of Off-the-Shelf Convolutional Neural Networks
Over recent years, a myriad of novel convolutional network architectures have been developed to advance state-of-the-art performance on challenging recognition tasks.
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environments
We then propose Mixture Outlier Exposure (MixOE), which mixes ID data and training outliers to expand the coverage of different OOD granularities, and trains the model such that the prediction confidence linearly decays as the input transitions from ID to OOD.
Medical Image Classification
Out-of-Distribution Detection
+1
NTIRE 2021 Multi-modal Aerial View Object Classification Challenge
In this paper, we introduce the first Challenge on Multi-modal Aerial View Object Classification (MAVOC) in conjunction with the NTIRE 2021 workshop at CVPR.
Tunable Hybrid Proposal Networks for the Open World
Current state-of-the-art object proposal networks are trained with a closed-world assumption, meaning they learn to only detect objects of the training classes.
Fine-grain Inference on Out-of-Distribution Data with Hierarchical Classification
Furthermore, we diagnose the classifiers performance at each level of the hierarchy improving the explainability and interpretability of the models predictions.
A Global Model Approach to Robust Few-Shot SAR Automatic Target Recognition
In the first, a global representation model is trained via self-supervised learning on a large pool of diverse and unlabeled SAR data.
SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection
Building up reliable Out-of-Distribution (OOD) detectors is challenging, often requiring the use of OOD data during training.
Establishing baselines and introducing TernaryMixOE for fine-grained out-of-distribution detection
Machine learning models deployed in the open world may encounter observations that they were not trained to recognize, and they risk misclassifying such observations with high confidence.
Adversarial Attacks on Foundational Vision Models
We show our attacks to be potent in whitebox and blackbox settings, as well as when transferred across foundational model types (e. g., attack DINOv2 with CLIP)!
Comprehensive OOD Detection Improvements
As machine learning becomes increasingly prevalent in impactful decisions, recognizing when inference data is outside the model's expected input distribution is paramount for giving context to predictions.
Dimensionality Reduction
Out of Distribution (OOD) Detection
Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble
Our experimental results demonstrate the superior performance of the MC Ensemble strategy in OOD detection compared to both the naive Deep Ensemble method and a standalone model of comparable size.
SoK: A Review of Differentially Private Linear Models For High-Dimensional Data
Linear models are ubiquitous in data science, but are particularly prone to overfitting and data memorization in high dimensions.
OSR-ViT: A Simple and Modular Framework for Open-Set Object Detection and Discovery
Our method also excels in low-data settings, outperforming supervised baselines using a fraction of the training data.
