Search Results for author:
Found 37 papers, 14 papers with code
Achieving the Tightest Relaxation of Sigmoids for Formal Verification
In the field of formal verification, Neural Networks (NNs) are typically reformulated into equivalent mathematical programs which are optimized over.
Verified Neural Compressed Sensing
Furthermore, we show that the complexity of the network (number of neurons/layers) can be adapted to the problem difficulty and solve problems where traditional compressed sensing methods are not known to provably work.
Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
Existing algorithms for differentially private continual counting are either inefficient in terms of their space usage or add an excessive amount of noise, inducing suboptimal utility.
Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
To investigate this issue in depth, we introduce the Text-Image Alignment Assessment (TIA2) benchmark, which comprises a diverse collection of text prompts, images, and human annotations.
Understanding Subjectivity through the Lens of Motivational Context in Model-Generated Image Satisfaction
Image generation models are poised to become ubiquitous in a range of applications.
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
We provide an improved analysis of standard differentially private gradient descent for linear regression under the squared error loss.
Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks
This paper presents a new bi-Lipschitz invertible neural network, the BiLipNet, which has the ability to smoothly control both its Lipschitzness (output sensitivity to input perturbations) and inverse Lipschitzness (input distinguishability from different outputs).
MINT: A wrapper to make multi-modal and multi-image AI models interactive
In this paper we tackle a more subtle challenge: doctors take a targeted medical history to obtain only the most pertinent pieces of information; how do we enable AI to do the same?
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
We characterize the asymptotic learning utility for any choice of the correlation function, giving precise analytical bounds for linear regression and as the solution to a convex program for general convex functions.
Learning to Receive Help: Intervention-Aware Concept Embedding Models
To address this, we propose Intervention-aware Concept Embedding models (IntCEMs), a novel CBM-based architecture and training paradigm that improves a model's receptiveness to test-time interventions.
Selective Concept Models: Permitting Stakeholder Customisation at Test-Time
Concept-based models perform prediction using a set of concepts that are interpretable to stakeholders.
Training Private Models That Know What They Don't Know
Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge.
Expressive Losses for Verified Robustness via Convex Combinations
In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain verifiability at the expense of standard performance.
Human Uncertainty in Concept-Based AI Systems
We study how existing concept-based models deal with uncertain interventions from humans using two novel datasets: UMNIST, a visual dataset with controlled simulated uncertainty based on the MNIST dataset, and CUB-S, a relabeling of the popular CUB concept dataset with rich, densely-annotated soft labels from humans.
Provably Bounding Neural Network Preimages
Most work on the formal verification of neural networks has focused on bounding the set of outputs that correspond to a given set of inputs (for example, bounded perturbations of a nominal input).
Interactive Concept Bottleneck Models
Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions.
IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound
Recent works have tried to increase the verifiability of adversarially trained networks by running the attacks over domains larger than the original perturbations and adding various regularization terms to the objective.
Role of Human-AI Interaction in Selective Prediction
Using real-world conservation data and a selective prediction system that improves expected accuracy over that of the human or AI system working individually, we show that this messaging has a significant impact on the accuracy of human judgements.
Overcoming the Convex Barrier for Simplex Inputs
Recent progress in neural network verification has challenged the notion of a convex barrier, that is, an inherent weakness in the convex relaxation of the output of a neural network.
A Fine-Grained Analysis on Distribution Shift
Despite this necessity, there has been little work in defining the underlying mechanisms that cause these shifts and evaluating the robustness of algorithms across multiple, different distribution shifts.
Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition
Finally, we design a BaB framework, named Branch and Dual Network Bound (BaDNB), based on our novel bounding and branching algorithms.
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications
In this direction, we first introduce a general formulation of probabilistic specifications for neural networks, which captures both probabilistic networks (e. g., Bayesian neural networks, MC-Dropout networks) and uncertain inputs (distributions over inputs arising from sensor noise or other perturbations).
Autoencoding Variational Autoencoder
We provide experimental results on the ColorMnist and CelebA benchmark datasets that quantify the properties of the learned representations and compare the approach with a baseline that is specifically trained for the desired property.
The Autoencoding Variational Autoencoder
We provide experimental results on the ColorMnist and CelebA benchmark datasets that quantify the properties of the learned representations and compare the approach with a baseline that is specifically trained for the desired property.
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
In this work, we propose a first-order dual SDP algorithm that (1) requires memory only linear in the total number of network activations, (2) only requires a fixed number of forward/backward passes through the network per iteration.
Lagrangian Decomposition for Neural Network Verification
Both the algorithms offer three advantages: (i) they yield bounds that are provably at least as tight as previous dual algorithms relying on Lagrangian relaxations; (ii) they are based on operations analogous to forward/backward pass of neural networks layers and are therefore easily parallelizable, amenable to GPU implementation and able to take advantage of the convolutional structure of problems; and (iii) they allow for anytime stopping while still providing valid bounds.
Achieving Robustness in the Wild via Adversarial Mixing with Disentangled Representations
Specifically, we leverage the disentangled latent representations computed by a StyleGAN model to generate perturbations of an image that are similar to real-world variations (like adding make-up, or changing the skin-tone of a person) and train models to be invariant to these perturbations.
Provenance detection through learning transformation-resilient watermarking
In this paper, we introduce ReSWAT (Resilient Signal Watermarking via Adversarial Training), a framework for learning transformation-resilient watermark detectors that are able to detect a watermark even after a signal has been through several post-processing transformations.
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks.
Adversarial Robustness through Local Linearization
Using this regularizer, we exceed current state of the art and achieve 47% adversarial accuracy for ImageNet with l-infinity adversarial perturbations of radius 4/255 under an untargeted, strong, white-box attack.
Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specifications
This behavior can have severe consequences such as usage of increased computation and induce faults in downstream modules that expect outputs of a certain length.
Verification of deep probabilistic models
For example, a machine translation model should produce semantically equivalent outputs for innocuous changes in the input to the model.
On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
Recent work has shown that it is possible to train deep neural networks that are provably robust to norm-bounded adversarial perturbations.
Training verified learners with learned verifiers
This paper proposes a new algorithmic framework, predictor-verifier training, to train neural networks that are verifiable, i. e., networks that provably satisfy some desired input-output properties.
Safe Exploration in Continuous Action Spaces
We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be violated.
Graphical Models for Optimal Power Flow
In this paper, we formulate the optimal power flow problem over tree networks as an inference problem over a tree-structured graphical model where the nodal variables are low-dimensional vectors.
Universal Convexification via Risk-Aversion
We develop a framework for convexifying a fairly general class of optimization problems.
