Search Results for author:
Found 24 papers, 10 papers with code
High-throughput Generative Inference of Large Language Models with a Single GPU
As a result, when running OPT-175B on a single 16GB GPU, FlexGen achieves significantly higher throughput compared to state-of-the-art offloading systems, reaching a generation throughput of 1 token/s for the first time with an effective batch size of 144.
Convex Bounds on the Softmax Function with Applications to Robustness Verification
The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well.
VeriX: Towards Verified Explainability of Deep Neural Networks
We present VeriX, a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models.
Tighter Abstract Queries in Neural Network Verification
Recent attempts have demonstrated that abstraction-refinement approaches could play a significant role in mitigating these limitations; but these approaches can often produce networks that are so abstract, that they become unsuitable for verification.
On Optimizing Back-Substitution Methods for Neural Network Verification
A key component in many state-of-the-art verification schemes is computing lower and upper bounds on the values that neurons in the network can obtain for a specific input domain -- and the tighter these bounds, the more likely the verification is to succeed.
Toward Certified Robustness Against Real-World Distribution Shifts
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts.
Neural Network Verification with Proof Production
In this work, we present a novel mechanism for enhancing Simplex-based DNN verifiers with proof production capabilities: the generation of an easy-to-check witness of unsatisfiability, which attests to the absence of errors.
Efficient Neural Network Analysis with Sum-of-Infeasibilities
Given a convex relaxation which over-approximates the non-convex activation functions, we encode the violations of activation functions as a cost function and optimize it with respect to the convex relaxation.
Scalable Verification of GNN-based Job Schedulers
Recently, Graph Neural Networks (GNNs) have been applied for scheduling jobs over clusters, achieving better performance than hand-crafted heuristics.
An Abstraction-Refinement Approach to Verifying Convolutional Neural Networks
Convolutional neural networks have gained vast popularity due to their excellent performance in the fields of computer vision, image processing, and others.
DeepCert: Verification of Contextually Relevant Robustness for Neural Network Image Classifiers
We introduce DeepCert, a tool-supported method for verifying the robustness of deep neural network (DNN) image classifiers to contextually relevant perturbations such as blur, haze, and changes in image contrast.
An SMT-Based Approach for Verifying Binarized Neural Networks
One novelty of our technique is that it allows the verification of neural networks that include both binarized and non-binarized components.
Global Optimization of Objective Functions Represented by ReLU Networks
However, individual "yes or no" questions cannot answer qualitative questions such as "what is the largest error within these bounds"; the answers to these lie in the domain of optimization.
Parallelization Techniques for Verifying Neural Networks
Inspired by recent successes with parallel optimization techniques for solving Boolean satisfiability, we investigate a set of strategies and heuristics that aim to leverage parallel computing to improve the scalability of neural network verification.
Verifying Recurrent Neural Networks using Invariant Inference
Deep neural networks are revolutionizing the way complex systems are developed.
G2SAT: Learning to Generate SAT Formulas
The Boolean Satisfiability (SAT) problem is the canonical NP-complete problem and is fundamental to computer science, with a wide array of applications in planning, verification, and theorem proving.
Simplifying Neural Networks using Formal Verification
Deep neural network (DNN) verification is an emerging field, with diverse verification engines quickly becoming available.
Algorithms for Verifying Deep Neural Networks
Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control.
Toward Scalable Verification for Safety-Critical Deep Networks
The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability.
Ground-Truth Adversarial Examples
We demonstrate how ground truths can serve to assess the effectiveness of attack techniques, by comparing the adversarial examples produced by those attacks to the ground truths; and also of defense techniques, by computing the distance to the ground truths before and after the defense is applied, and measuring the improvement.
DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
We propose a novel approach for automatically identifying safe regions of the input space, within which the network is robust against adversarial perturbations.
Provably Minimally-Distorted Adversarial Examples
Using this approach, we demonstrate that one of the recent ICLR defense proposals, adversarial retraining, provably succeeds at increasing the distortion required to construct adversarial examples by a factor of 4. 2.
Towards Proving the Adversarial Robustness of Deep Neural Networks
Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations.
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Deep neural networks have emerged as a widely used and effective means for tackling complex, real-world problems.
