Expressive Losses for Verified Robustness via Convex Combinations

23 May 2023

Alessandro De Palma

Rudy Bunel

Krishnamurthy Dvijotham

Papers citing "Expressive Losses for Verified Robustness via Convex Combinations"

29 / 29 papers shown

Title
Average Certified Radius is a Poor Metric for Randomized Smoothing Chenhao Sun Yuhao Mao Mark Niklas Muller Martin Vechev AAML 63 0 0 09 Oct 2024
On Using Certified Training towards Empirical Robustness Alessandro De Palma Serge Durand Zakaria Chihani François Terrier Caterina Urban OOD AAML 67 1 0 02 Oct 2024
CTBENCH: A Library and Benchmark for Certified Training Yuhao Mao Stefan Balauca Martin Vechev OOD 75 5 0 07 Jun 2024
Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models Naman D. Singh Francesco Croce Matthias Hein OOD 67 65 0 03 Mar 2023
Improved techniques for deterministic l2 robustness Sahil Singla Soheil Feizi AAML 59 10 0 15 Nov 2022
Certified Training: Small Boxes are All You Need Mark Niklas Muller Franziska Eckert Marc Fischer Martin Vechev AAML 53 47 0 10 Oct 2022
Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective Bohang Zhang Du Jiang Di He Liwei Wang OOD 59 50 0 04 Oct 2022
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound Claudio Ferrari Mark Niklas Muller Nikola Jovanović Martin Vechev 67 86 0 30 Apr 2022
In Defense of the Unitary Scalarization for Deep Multi-Task Learning Vitaly Kurin Alessandro De Palma Ilya Kostrikov Shimon Whiteson M. P. Kumar 69 74 0 11 Jan 2022
Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds Yujia Huang Huan Zhang Yuanyuan Shi J Zico Kolter Anima Anandkumar 71 78 0 02 Nov 2021
The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Results Stanley Bak Changliu Liu Taylor T. Johnson NAI 73 112 0 31 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 105 5 0 11 Jul 2021
Orthogonalizing Convolutional Layers with the Cayley Transform Asher Trockman J. Zico Kolter 53 113 0 14 Apr 2021
PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximations Mark Niklas Muller Gleb Makarchuk Gagandeep Singh Markus Püschel Martin Vechev 61 91 0 05 Mar 2021
On the Paradox of Certified Training Nikola Jovanović Mislav Balunović Maximilian Baader Martin Vechev OOD 40 13 0 12 Feb 2021
Scaling the Convex Barrier with Sparse Dual Algorithms Alessandro De Palma Harkirat Singh Behl Rudy Bunel Philip Torr M. P. Kumar 79 9 0 14 Jan 2021
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming Sumanth Dathathri Krishnamurthy Dvijotham Alexey Kurakin Aditi Raghunathan J. Uesato ... Shreya Shankar Jacob Steinhardt Ian Goodfellow Percy Liang Pushmeet Kohli AAML 84 93 0 22 Oct 2020
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks Francesco Croce Matthias Hein AAML 211 1,837 0 03 Mar 2020
Lagrangian Decomposition for Neural Network Verification Rudy Bunel Alessandro De Palma Alban Desmaison Krishnamurthy Dvijotham Pushmeet Kohli Philip Torr M. P. Kumar 47 50 0 24 Feb 2020
Towards Stable and Efficient Training of Verifiably Robust Neural Networks Huan Zhang Hongge Chen Chaowei Xiao Sven Gowal Robert Stanforth Yue Liu Duane S. Boning Cho-Jui Hsieh AAML 67 346 0 14 Jun 2019
Certified Adversarial Robustness via Randomized Smoothing Jeremy M. Cohen Elan Rosenfeld J. Zico Kolter AAML 130 2,028 0 08 Feb 2019
Strong mixed-integer programming formulations for trained neural networks Ross Anderson Joey Huchette Christian Tjandraatmadja J. Vielma 135 255 0 20 Nov 2018
Adversarial Risk and the Dangers of Evaluating Against Weak Attacks J. Uesato Brendan O'Donoghue Aaron van den Oord Pushmeet Kohli AAML 145 601 0 15 Feb 2018
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples Anish Athalye Nicholas Carlini D. Wagner AAML 195 3,180 0 01 Feb 2018
A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets P. Chrabaszcz I. Loshchilov Frank Hutter SSeg OOD 139 645 0 27 Jul 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 277 12,029 0 19 Jun 2017
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks Guy Katz Clark W. Barrett D. Dill Kyle D. Julian Mykel Kochenderfer AAML 301 1,860 0 03 Feb 2017
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift Sergey Ioffe Christian Szegedy OOD 430 43,234 0 11 Feb 2015
Intriguing properties of neural networks Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna D. Erhan Ian Goodfellow Rob Fergus AAML 247 14,893 1 21 Dec 2013