research
∙
05/12/2023
Monitoring and Adapting ML Models on Mobile Devices
ML models are increasingly being pushed to mobile devices, for low-laten...
share
research
∙
03/22/2023
Test-time Defense against Adversarial Attacks: Detection and Reconstruction of Adversarial Examples via Masked Autoencoder
Existing defense methods against adversarial attacks can be categorized ...
research
∙
03/01/2023
Self-Supervised Convolutional Visual Prompts
Machine learning models often fail on out-of-distribution (OOD) samples....
research
∙
12/14/2022
Understanding Zero-Shot Adversarial Robustness for Large-Scale Models
Pretrained large-scale vision-language models like CLIP have exhibited s...
research
∙
12/13/2022
Adversarially Robust Video Perception by Seeing Motion
Despite their excellent performance, state-of-the-art computer vision mo...
research
∙
12/12/2022
Doubly Right Object Recognition: A Why Prompt for Visual Rationales
Many visual recognition models are evaluated only on their classificatio...
research
∙
12/12/2022
Robust Perception through Equivariance
Deep networks for computer vision are not reliable when they encounter a...
research
∙
10/07/2022
1st ICLR International Workshop on Privacy, Accountability, Interpretability, Robustness, Reasoning on Structured Data (PAIR^2Struct)
Recent years have seen advances on principles and guidance relating to a...
research
∙
06/17/2022
Landscape Learning for Neural Network Inversion
Many machine learning methods operate by inverting a neural network at i...
research
∙
06/17/2022
Shadows Shed Light on 3D Objects
3D reconstruction is a fundamental problem in computer vision, and the t...
research
∙
04/26/2022
Causal Transportability for Visual Recognition
Visual representations underlie object recognition tasks, but they often...
research
∙
04/22/2022
A Tale of Two Models: Constructing Evasive Attacks on Edge Models
Full-precision deep learning models are typically too large or costly to...
research
∙
04/07/2022
Using Multiple Self-Supervised Tasks Improves Model Robustness
Deep networks achieve state-of-the-art performance on computer vision ta...
research
∙
12/14/2021
Real-Time Neural Voice Camouflage
Automatic speech recognition systems have created exciting possibilities...
research
∙
11/20/2021
Discrete Representations Strengthen Vision Transformer Robustness
Vision Transformer (ViT) is emerging as the state-of-the-art architectur...
research
∙
03/26/2021
Adversarial Attacks are Reversible with Natural Supervision
We find that images contain intrinsic structure that enables the reversa...
research
∙
12/22/2020
Generative Interventions for Causal Learning
We introduce a framework for learning robust visual representations that...
research
∙
07/14/2020
Multitask Learning Strengthens Adversarial Robustness
Although deep networks achieve strong accuracy on a range of computer vi...
research
∙
04/22/2020
Live Trojan Attacks on Deep Neural Networks
Like all software systems, the execution of deep learning models is dict...
research
∙
10/06/2019
Unrestricted Adversarial Attacks for Semantic Segmentation
Semantic segmentation is one of the most impactful applications of machi...
research
∙
09/03/2019
Metric Learning for Adversarial Robustness
Deep networks are well-known to be fragile to adversarial attacks. Using...
research
∙
02/06/2019