Search Results for author: Clark Barrett

Found 35 papers, 20 papers with code

Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates

no code implementations22 May 2024 Udayan Mandal, Guy Amir, Haoze Wu, Ieva Daukantas, Fletcher Lee Newell, Umberto J. Ravaioli, Baoluo Meng, Michael Durling, Milan Ganai, Tobey Shim, Guy Katz, Clark Barrett

A promising approach for providing strong guarantees on an agent's behavior is to use Neural Lyapunov Barrier (NLB) certificates, which are learned functions over the system whose properties indirectly imply that an agent behaves as desired.

reinforcement-learning

Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

no code implementations10 May 2024 David "davidad" Dalrymple, Joar Skalse, Yoshua Bengio, Stuart Russell, Max Tegmark, Sanjit Seshia, Steve Omohundro, Christian Szegedy, Ben Goldhaber, Nora Ammann, Alessandro Abate, Joe Halpern, Clark Barrett, Ding Zhao, Tan Zhi-Xuan, Jeannette Wing, Joshua Tenenbaum

Ensuring that AI systems reliably and robustly avoid harmful or dangerous behaviours is a crucial challenge, especially for AI systems with a high degree of autonomy and general intelligence, or systems used in safety-critical contexts.

Markovian Agents for Informative Language Modeling

no code implementations29 Apr 2024 Scott Viteri, Max Lamparth, Peter Chatain, Clark Barrett

We derive a "Markovian training" procedure by applying our definition of informativeness to a Markovian LM and optimizing via policy gradient and Proximal Policy Optimization (PPO).

Informativeness Language Modelling

Towards Efficient Verification of Quantized Neural Networks

1 code implementation20 Dec 2023 Pei Huang, Haoze Wu, Yuting Yang, Ieva Daukantas, Min Wu, Yedi Zhang, Clark Barrett

Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory.

Quantization

Clover: Closed-Loop Verifiable Code Generation

1 code implementation26 Oct 2023 Chuyue Sun, Ying Sheng, Oded Padon, Clark Barrett

The use of large language models for code generation is a rapidly growing trend in software development.

Code Generation

Lemur: Integrating Large Language Models in Automated Program Verification

1 code implementation7 Oct 2023 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 reasoning about program properties that is challenging for verification tools.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

1 code implementation24 Jun 2023 Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark Barrett, Zhangyang Wang, Beidi Chen

Based on these insights, we propose Heavy Hitter Oracle (H$_2$O), a KV cache eviction policy that dynamically retains a balance of recent and H$_2$ tokens.

On Optimal Caching and Model Multiplexing for Large Model Inference

1 code implementation3 Jun 2023 Banghua Zhu, Ying Sheng, Lianmin Zheng, Clark Barrett, Michael I. Jordan, Jiantao Jiao

Theoretically, we provide an optimal algorithm for jointly optimizing both approaches to reduce the inference cost in both offline and online tabular settings.

Lightweight Online Learning for Sets of Related Problems in Automated Reasoning

1 code implementation18 May 2023 Haoze Wu, Christopher Hahn, Florian Lonsing, Makai Mann, Raghuram Ramanujan, Clark Barrett

We present Self-Driven Strategy Learning ($\textit{sdsl}$), a lightweight online learning methodology for automated reasoning tasks that involve solving a set of related problems.

FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

1 code implementation13 Mar 2023 Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Daniel Y. Fu, Zhiqiang Xie, Beidi Chen, Clark Barrett, Joseph E. Gonzalez, Percy Liang, Christopher Ré, Ion Stoica, Ce Zhang

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.

Language Modelling Large Language Model

Convex Bounds on the Softmax Function with Applications to Robustness Verification

1 code implementation3 Mar 2023 Dennis Wei, Haoze Wu, Min Wu, Pin-Yu Chen, Clark Barrett, Eitan Farchi

The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well.

Tighter Abstract Queries in Neural Network Verification

1 code implementation23 Oct 2022 Elazar Cohen, Yizhak Yisrael Elboher, Clark Barrett, Guy Katz

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

no code implementations16 Aug 2022 Tom Zelazny, Haoze Wu, Clark Barrett, Guy Katz

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

1 code implementation8 Jun 2022 Haoze Wu, Teruhiro Tagomori, Alexander Robey, Fengjun Yang, Nikolai Matni, George Pappas, Hamed Hassani, Corina Pasareanu, Clark Barrett

We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts.

Neural Network Verification with Proof Production

no code implementations1 Jun 2022 Omri Isac, Clark Barrett, Min Zhang, Guy Katz

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.

Collision Avoidance LEMMA

Efficient Neural Network Analysis with Sum-of-Infeasibilities

2 code implementations19 Mar 2022 Haoze Wu, Aleksandar Zeljić, Guy Katz, Clark Barrett

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.

Adversarial Attack Efficient Neural Network

Scalable Verification of GNN-based Job Schedulers

1 code implementation7 Mar 2022 Haoze Wu, Clark Barrett, Mahmood Sharif, Nina Narodytska, Gagandeep Singh

Recently, Graph Neural Networks (GNNs) have been applied for scheduling jobs over clusters, achieving better performance than hand-crafted heuristics.

Scheduling

An Abstraction-Refinement Approach to Verifying Convolutional Neural Networks

no code implementations6 Jan 2022 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.

DeepCert: Verification of Contextually Relevant Robustness for Neural Network Image Classifiers

no code implementations2 Mar 2021 Colin Paterson, Haoze Wu, John Grese, Radu Calinescu, Corina S. Pasareanu, Clark Barrett

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

1 code implementation5 Nov 2020 Guy Amir, Haoze Wu, Clark Barrett, Guy Katz

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

no code implementations7 Oct 2020 Christopher A. Strong, Haoze Wu, Aleksandar Zeljić, Kyle D. Julian, Guy Katz, Clark Barrett, Mykel J. Kochenderfer

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

no code implementations17 Apr 2020 Haoze Wu, Alex Ozdemir, Aleksandar Zeljić, Ahmed Irfan, Kyle Julian, Divya Gopinath, Sadjad Fouladi, Guy Katz, Corina Pasareanu, Clark Barrett

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

1 code implementation6 Apr 2020 Yuval Jacoby, Clark Barrett, Guy Katz

Deep neural networks are revolutionizing the way complex systems are developed.

G2SAT: Learning to Generate SAT Formulas

1 code implementation NeurIPS 2019 Jiaxuan You, Haoze Wu, Clark Barrett, Raghuram Ramanujan, Jure Leskovec

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.

Automated Theorem Proving

Simplifying Neural Networks using Formal Verification

no code implementations25 Oct 2019 Sumathi Gokulanathan, Alexander Feldsher, Adi Malca, Clark Barrett, Guy Katz

Deep neural network (DNN) verification is an emerging field, with diverse verification engines quickly becoming available.

Collision Avoidance

Algorithms for Verifying Deep Neural Networks

2 code implementations15 Mar 2019 Changliu Liu, Tomer Arnon, Christopher Lazarus, Clark Barrett, Mykel J. Kochenderfer

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

no code implementations18 Jan 2018 Lindsey Kuper, Guy Katz, Justin Gottschlich, Kyle Julian, Clark Barrett, Mykel Kochenderfer

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.

Autonomous Driving

Ground-Truth Adversarial Examples

no code implementations ICLR 2018 Nicholas Carlini, Guy Katz, Clark Barrett, David L. Dill

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

no code implementations2 Oct 2017 Divya Gopinath, Guy Katz, Corina S. Pasareanu, Clark Barrett

We propose a novel approach for automatically identifying safe regions of the input space, within which the network is robust against adversarial perturbations.

Adversarial Robustness Clustering +4

Provably Minimally-Distorted Adversarial Examples

1 code implementation29 Sep 2017 Nicholas Carlini, Guy Katz, Clark Barrett, David L. Dill

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.

Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

8 code implementations3 Feb 2017 Guy Katz, Clark Barrett, David Dill, Kyle Julian, Mykel Kochenderfer

Deep neural networks have emerged as a widely used and effective means for tackling complex, real-world problems.

Collision Avoidance

Cannot find the paper you are looking for? You can Submit a new open access paper.