Certified Training: Small Boxes are All You Need

10 October 2022

Martin Vechev

Papers citing "Certified Training: Small Boxes are All You Need"

32 / 32 papers shown

Title
Support is All You Need for Certified VAE Training Changming Xu Debangshu Banerjee Deepak Vasisht Gagandeep Singh AAML 39 0 0 16 Apr 2025
Defending against Adversarial Malware Attacks on ML-based Android Malware Detection Systems Ping He Lorenzo Cavallaro Shouling Ji AAML 37 0 0 23 Jan 2025
Certified Training with Branch-and-Bound: A Case Study on Lyapunov-stable Neural Control Zhouxing Shi Cho-Jui Hsieh Huan Zhang 70 0 0 27 Nov 2024
Average Certified Radius is a Poor Metric for Randomized Smoothing Chenhao Sun Yuhao Mao Mark Niklas Muller Martin Vechev AAML 36 0 0 09 Oct 2024
Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagation Hanjiang Hu Yujie Yang Tianhao Wei Changliu Liu AAML 24 6 0 04 Oct 2024
Towards Universal Certified Robustness with Multi-Norm Training Enyi Jiang Gagandeep Singh Gagandeep Singh AAML 55 1 0 03 Oct 2024
On Using Certified Training towards Empirical Robustness Alessandro De Palma Serge Durand Zakaria Chihani François Terrier Caterina Urban OOD AAML 33 1 0 02 Oct 2024
Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness Erh-Chung Chen Pin-Yu Chen I-Hsin Chung Che-Rung Lee 32 2 0 28 Jun 2024
Certified Robustness to Data Poisoning in Gradient-Based Training Philip Sosnin Mark N. Müller Maximilian Baader Calvin Tsay Matthew Wicker AAML SILM 63 8 0 09 Jun 2024
CTBENCH: A Library and Benchmark for Certified Training Yuhao Mao Stefan Balauca Martin Vechev OOD 41 4 0 07 Jun 2024
How Does Bayes Error Limit Probabilistic Robust Accuracy Ruihan Zhang Jun Sun AAML 27 1 0 23 May 2024
Towards Certification of Uncertainty Calibration under Adversarial Attacks Cornelius Emde Francesco Pinto Thomas Lukasiewicz Philip H. S. Torr Adel Bibi AAML 38 0 0 22 May 2024
Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors Ruihan Zhang Jun Sun AAML 24 3 0 19 May 2024
Cross-Input Certified Training for Universal Perturbations Changming Xu Gagandeep Singh AAML 23 2 0 15 May 2024
Towards Precise Observations of Neural Model Robustness in Classification Wenchuan Mu Kwan Hui Lim AAML 16 0 0 25 Apr 2024
Is Adversarial Training with Compressed Datasets Effective? Tong Chen Raghavendra Selvan AAML 48 0 0 08 Feb 2024
Set-Based Training for Neural Network Verification Lukas Koller Tobias Ladner Matthias Althoff AAML 43 1 0 26 Jan 2024
Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors Biagio Montaruli Luca Demetrio Maura Pintor Luca Compagna Davide Balzarotti Battista Biggio AAML 24 5 0 04 Oct 2023
Towards Certified Probabilistic Robustness with High Accuracy Ruihan Zhang Peixin Zhang Jun Sun AAML 19 0 0 02 Sep 2023
Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs Zhakshylyk Nurlanov Frank R. Schmidt Florian Bernard OOD 16 0 0 24 Jul 2023
Understanding Certified Training with Interval Bound Propagation Yuhao Mao Mark Niklas Muller Marc Fischer Martin Vechev AAML 41 14 0 17 Jun 2023
How robust accuracy suffers from certified training with convex relaxations Piersilvio De Bartolomeis Jacob Clarysse Amartya Sanyal Fanny Yang AAML 18 2 0 12 Jun 2023
Expressive Losses for Verified Robustness via Convex Combinations Alessandro De Palma Rudy Bunel Krishnamurthy Dvijotham M. P. Kumar Robert Stanforth A. Lomuscio AAML 28 11 0 23 May 2023
DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation Haitham Khedr Yasser Shoukry 34 4 0 22 May 2023
TAPS: Connecting Certified and Adversarial Training Yuhao Mao Mark Niklas Muller Marc Fischer Martin Vechev AAML 13 10 0 08 May 2023
Verifiable Learning for Robust Tree Ensembles Stefano Calzavara Lorenzo Cazzaro Giulio Ermanno Pibiri N. Prezza AAML 21 2 0 05 May 2023
Efficient Certified Training and Robustness Verification of Neural ODEs Mustafa Zeqiri Mark Niklas Muller Marc Fischer Martin Vechev AAML 22 2 0 09 Mar 2023
PECAN: A Deterministic Certified Defense Against Backdoor Attacks Yuhao Zhang Aws Albarghouthi Loris Dántoni AAML 20 4 0 27 Jan 2023
First Three Years of the International Verification of Neural Networks Competition (VNN-COMP) Christopher Brix Mark Niklas Muller Stanley Bak Taylor T. Johnson Changliu Liu NAI 25 66 0 14 Jan 2023
Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks Mathias Lechner Dorde Zikelic K. Chatterjee T. Henzinger Daniela Rus AAML 11 2 0 29 Nov 2022
SoK: Certified Robustness for Deep Neural Networks Linyi Li Tao Xie Bo-wen Li AAML 11 128 0 09 Sep 2020
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks Guy Katz Clark W. Barrett D. Dill Kyle D. Julian Mykel Kochenderfer AAML 222 1,835 0 03 Feb 2017