On the Tightness of Semidefinite Relaxations for Certifying Robustness
to Adversarial Examples

v1v2 (latest)

On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples

11 June 2020

Richard Y. Zhang

ArXiv (abs)PDF HTML

Papers citing "On the Tightness of Semidefinite Relaxations for Certifying Robustness to Adversarial Examples"

13 / 13 papers shown

Title
Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation Ben Batten Yang Zheng Alessandro De Palma Panagiotis Kouvaros A. Lomuscio AAML 76 1 0 23 Aug 2024
Convex Relaxation for Solving Large-Margin Classifiers in Hyperbolic Space Sheng Yang Peihan Liu Cengiz Pehlevan 81 0 0 27 May 2024
Local Lipschitz Constant Computation of ReLU-FNNs: Upper Bound Computation with Exactness Verification Y. Ebihara Xin Dai Victor Magron D. Peaucelle Sophie Tarbouriech 25 5 0 17 Oct 2023
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 160 37 0 29 Apr 2023
Efficient Symbolic Reasoning for Neural-Network Verification Zi Wang S. Jha Krishnamurthy Dvijotham Dvijotham AAML NAI 94 2 0 23 Mar 2023
Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations Hong-Ming Chiu Richard Y. Zhang AAML 76 3 0 30 Nov 2022
On the tightness of linear relaxation based robustness certification methods Cheng Tang AAML 79 0 0 01 Oct 2022
An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models Brendon G. Anderson Tanmay Gautam Somayeh Sojoudi OOD 53 2 0 15 Aug 2022
A Unified View of SDP-based Neural Network Verification through Completely Positive Programming Robin Brown Edward Schmerling Navid Azizan Marco Pavone AAML 73 17 0 06 Mar 2022
Advances in adversarial attacks and defenses in computer vision: A survey Naveed Akhtar Ajmal Mian Navid Kardan M. Shah AAML 162 242 0 01 Aug 2021
Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks Kendra Albert Maggie K. Delano B. Kulynych Ramnath Kumar AAML 133 5 0 11 Jul 2021
Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification Brendon G. Anderson Ziye Ma Jingqi Li Somayeh Sojoudi 128 1 0 22 Jan 2021
A Sequential Framework Towards an Exact SDP Verification of Neural Networks Ziye Ma Somayeh Sojoudi 57 8 0 16 Oct 2020