55 citations · 151 across the 24 of their papers we have counts for
24 papers
Lookahead Branching for Neural Network Verification
Liam Davis, Duo Zhou, Huan Zhang +3
In this work, we investigate the effect of lookahead branching strategies in neural network verification. We present a general recipe to integrate lookahead into any branch-and-bou…
Proof Minimization in Neural Network Verification
Omri Isac, Idan Refaeli, Haoze Wu +2
The widespread adoption of deep neural networks (DNNs) requires efficient techniques for verifying their safety. DNN verifiers are complex tools, which might contain bugs that coul…
Cubing for Tuning
Haoze Wu, Clark Barrett, Nina Narodytska
We are exploring the problem of building an automated reasoning procedure that adaptively tunes the high-level solving strategy for a given problem. There are two main distinctive…
PICID: Proof-Driven Clause Learning in Neural Network Verification
Omri Isac, Idan Refaeli, Haoze Wu +2
Current Deep Neural Network (DNN) verifiers are typically designed to prioritize scalability over reliability. Reliability can be reinforced through the generation of proofs that a…
Efficiently Computing Compact Formal Explanations
Min Wu, Xiaofu Li, Haoze Wu +1
Building on VeriX (Verified eXplainability, arXiv:2212.01051), a system for producing optimal verified explanations for machine learning models, we present VeriX+, which significan…
Safe and Reliable Training of Learning-Based Aerospace Controllers
Udayan Mandal, Guy Amir, Haoze Wu +10
In recent years, deep reinforcement learning (DRL) approaches have generated highly successful controllers for a myriad of complex domains. However, the opaque nature of these mode…
Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates
Udayan Mandal, Guy Amir, Haoze Wu +9
Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating agents that control autonomous systems. However, the ``black box'' nature of DRL agents lim…
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
Haoze Wu, Omri Isac, Aleksandar Zeljić +14
This paper serves as a comprehensive system description of version 2.0 of the Marabou framework for formal analysis of neural networks. We discuss the tool's architectural design a…
Towards Efficient Verification of Quantized Neural Networks
Pei Huang, Haoze Wu, Yuting Yang +4
Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory. In t…
Lemur: Integrating Large Language Models in Automated Program Verification
Haoze Wu, Clark Barrett, Nina Narodytska
The demonstrated code-understanding capability of LLMs raises the question of whether they can be used for automated program verification, a task that demands high-level abstract r…
Identifying and Mitigating the Security Risks of Generative AI
Clark Barrett, Brad Boyd, Elie Burzstein +20
Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, s…
HO: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Zhenyu Zhang, Ying Sheng, Tianyi Zhou +9
Large Language Models (LLMs), despite their recent impressive accomplishments, are notably cost-prohibitive to deploy, particularly for applications involving long-content generati…
On Optimal Caching and Model Multiplexing for Large Model Inference
Banghua Zhu, Ying Sheng, Lianmin Zheng +3
Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. In…
Lightweight Online Learning for Sets of Related Problems in Automated Reasoning
Haoze Wu, Christopher Hahn, Florian Lonsing +3
We present Self-Driven Strategy Learning (), a lightweight online learning methodology for automated reasoning tasks that involve solving a set of related problems.…
Convex Bounds on the Softmax Function with Applications to Robustness Verification
Dennis Wei, Haoze Wu, Min Wu +3
The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well. This paper provides convex lower bounds and concave…
Soy: An Efficient MILP Solver for Piecewise-Affine Systems
Haoze Wu, Min Wu, Dorsa Sadigh +1
Piecewise-affine (PWA) systems are widely used for modeling and control of robotics problems including modeling contact dynamics. A common approach is to encode the control problem…
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
Ying Sheng, Lianmin Zheng, Binhang Yuan +11
The high computational and memory requirements of large language model (LLM) inference make it feasible only with multiple high-end accelerators. Motivated by the emerging demand f…
VeriX: Towards Verified Explainability of Deep Neural Networks
Min Wu, Haoze Wu, Clark Barrett
We present VeriX (Verified eXplainability), a system for producing optimal robust explanations and generating counterfactuals along decision boundaries of machine learning models.…
Tighter Abstract Queries in Neural Network Verification
Elazar Cohen, Yizhak Yisrael Elboher, Clark Barrett +1
Neural networks have become critical components of reactive systems in various domains within computer science. Despite their excellent performance, using neural networks entails n…
On Optimizing Back-Substitution Methods for Neural Network Verification
Tom Zelazny, Haoze Wu, Clark Barrett +1
With the increasing application of deep learning in mission-critical systems, there is a growing need to obtain formal guarantees about the behaviors of neural networks. Indeed, ma…
Toward Certified Robustness Against Real-World Distribution Shifts
Haoze Wu, Teruhiro Tagomori, Alexander Robey +6
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts. To do so, we bridge the gap between hand-crafted specifications…
Neural Network Verification with Proof Production
Omri Isac, Clark Barrett, Min Zhang +1
Deep neural networks (DNNs) are increasingly being employed in safety-critical systems, and there is an urgent need to guarantee their correctness. Consequently, the verification c…
Efficient Neural Network Analysis with Sum-of-Infeasibilities
Haoze Wu, Aleksandar Zeljić, Guy Katz +1
Inspired by sum-of-infeasibilities methods in convex optimization, we propose a novel procedure for analyzing verification queries on neural networks with piecewise-linear activati…
An Abstraction-Refinement Approach to Verifying Convolutional Neural Networks
Matan Ostrovsky, Clark Barrett, Guy Katz
Convolutional neural networks have gained vast popularity due to their excellent performance in the fields of computer vision, image processing, and others. Unfortunately, it is no…