research
∙
09/07/2023
Adapting Self-Supervised Representations to Multi-Domain Setups
Current state-of-the-art self-supervised approaches, are effective when ...
share
research
∙
09/06/2023
Certifying LLM Safety against Adversarial Prompting
Large language models (LLMs) released for public use incorporate guardra...
research
∙
08/28/2023
Identifying and Mitigating the Security Risks of Generative AI
Every major technical invention resurfaces the dual-use dilemma – the ne...
research
∙
07/20/2023
Identifying Interpretable Subspaces in Image Representations
We propose Automatic Feature Explanation using Contrasting Concepts (FAL...
research
∙
07/18/2023
Augmenting CLIP with Improved Visio-Linguistic Reasoning
Image-text contrastive models such as CLIP are useful for a variety of d...
research
∙
05/31/2023
Diffused Redundancy in Pre-trained Representations
Representations learned by pre-training a neural network on a large data...
research
∙
05/10/2023
Text-To-Concept (and Back) via Cross-Model Alignment
We observe that the mapping between an image's representation in one mod...
research
∙
04/04/2023
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
Few-shot classification (FSC) entails learning novel classes given only ...
research
∙
03/28/2023
Provable Robustness for Streaming Models with a Sliding Window
The literature on provable robustness in machine learning has primarily ...
research
∙
03/07/2023
CUDA: Convolution-based Unlearnable Datasets
Large-scale training of modern deep learning models heavily relies on pu...
research
∙
02/05/2023
Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
In data poisoning attacks, an adversary tries to change a model's predic...
research
∙
11/26/2022
Towards Better Input Masking for Convolutional Neural Networks
The ability to remove features from the input of machine learning models...
research
∙
11/18/2022
Invariant Learning via Diffusion Dreamed Distribution Shifts
Though the background is an important signal for image classification, o...
research
∙
11/15/2022
Improved techniques for deterministic l2 robustness
Training convolutional neural networks (CNNs) with a strict 1-Lipschitz ...
research
∙
09/15/2022
Explicit Tradeoffs between Adversarial and Natural Distributional Robustness
Several existing works study either adversarial or natural distributiona...
research
∙
08/28/2022
Goal-Conditioned Q-Learning as Knowledge Distillation
Many applications of reinforcement learning can be formalized as goal-co...
research
∙
06/21/2022
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems
Communication is important in many multi-agent reinforcement learning (M...
research
∙
06/05/2022
Interpretable Mixture of Experts for Structured Data
With the growth of machine learning for structured data, the need for re...
research
∙
03/28/2022
Core Risk Minimization using Salient ImageNet
Deep neural networks can be unreliable in the real world especially when...
research
∙
03/16/2022
Provable Adversarial Robustness for Fractional Lp Threat Models
In recent years, researchers have extensively studied adversarial robust...
research
∙
03/03/2022
Understanding Failure Modes of Self-Supervised Learning
Self-supervised learning methods have shown impressive results in downst...
research
∙
01/28/2022
Certifying Model Accuracy under Distribution Shifts
Certified robustness in machine learning has primarily focused on advers...
research
∙
01/26/2022
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes
While datasets with single-label supervision have propelled rapid advanc...
research
∙
12/12/2021
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses
Adversarial training (AT) is considered to be one of the most reliable d...
research
∙
12/09/2021
Mutual Adversarial Training: Learning together is better than going alone
Recent studies have shown that robustness to adversarial attacks can be ...
research
∙
12/08/2021
Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection
Object detection plays a key role in many security-critical systems. Adv...
research
∙
11/29/2021
Improving Deep Learning Interpretability by Saliency Guided Training
Saliency methods have been widely used to highlight important input feat...
research
∙
10/21/2021
On Hard Episodes in Meta-Learning
Existing meta-learners primarily focus on improving the average task acc...
research
∙
10/08/2021
Causal ImageNet: How to discover spurious features in Deep Learning?
A key reason for the lack of reliability of deep neural networks in the ...
research
∙
10/07/2021
FOCUS: Familiar Objects in Common and Uncommon Settings
Standard training datasets for deep learning often contain objects in co...
research
∙
08/30/2021
Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings
Adversarial robustness of deep models is pivotal in ensuring safe deploy...
research
∙
08/05/2021
Householder Activations for Provable Robustness against Adversarial Attacks
Training convolutional neural networks (CNNs) with a strict Lipschitz co...
research
∙
06/21/2021
Policy Smoothing for Provably Robust Reinforcement Learning
The study of provable adversarial robustness for deep neural network (DN...
research
∙
05/24/2021
Skew Orthogonal Convolutions
Training convolutional neural networks with a Lipschitz constraint under...
research
∙
04/12/2021
Understanding Overparameterization in Generative Adversarial Networks
A broad class of unsupervised deep learning methods such as Generative A...
research
∙
03/17/2021
Improved, Deterministic Smoothing for L1 Certified Robustness
Randomized smoothing is a general technique for computing sample-depende...
research
∙
02/15/2021
Low Curvature Activations Reduce Overfitting in Adversarial Training
Adversarial training is one of the most effective defenses against adver...
research
∙
10/26/2020
Benchmarking Deep Learning Interpretability in Time Series Predictions
Saliency methods are used extensively to highlight the importance of inp...
research
∙
10/20/2020
Tight Second-Order Certificates for Randomized Smoothing
Randomized smoothing is a popular way of providing robustness guarantees...
research
∙
10/12/2020
Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
Optimal Transport (OT) distances such as Wasserstein have been used in s...
research
∙
10/05/2020
Winning Lottery Tickets in Deep Generative Models
The lottery ticket hypothesis suggests that sparse, sub-networks of a gi...
research
∙
09/24/2020
GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue
Building on the success of deep learning, Generative Adversarial Network...
research
∙
09/17/2020
Certifying Confidence via Randomized Smoothing
Randomized smoothing has been shown to provide good certified-robustness...
research
∙
09/05/2020
Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks
Adversarial training is a popular defense strategy against attack threat...
research
∙
06/26/2020
Deep Partition Aggregation: Provable Defense against General Poisoning Attacks
Adversarial poisoning attacks distort training data in order to corrupt ...
research
∙
06/25/2020
Influence Functions in Deep Learning Are Fragile
Influence functions approximate the effect of training samples in test-t...
research
∙
06/22/2020
Perceptual Adversarial Robustness: Defense Against Unseen Threat Models
We present adversarial attacks and defenses for the perceptual adversari...
research
∙
06/17/2020
Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
Deep neural networks are being increasingly used in real world applicati...
research
∙
06/01/2020
Second-Order Provable Defenses against Adversarial Attacks
A robustness certificate is the minimum distance of a given input to the...
research
∙
03/02/2020