paper-with-me

홈 › Papers

Fast and Effective Robustness Certification

2018-12-01 · NeurIPS 2018 12 · Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin Vechev

We present a new method and system, called DeepZ, for certifying neural network robustness based on abstract interpretation. Compared to state-of-the-art automated verifiers for neural networks, DeepZ: (i) handles ReLU, Tanh and Sigmoid activation functions, (ii) supports feedforward and convolutional architectures, (iii) is significantly more scalable and precise, and (iv) and is sound with respect to floating point arithmetic. These benefits are due to carefully designed approximations tailored to the setting of neural networks. As an example, DeepZ achieves a verification accuracy of 97% on a large network with 88,500 hidden units under $L_{\infty}$ attack with $\epsilon = 0.1$ with an average runtime of 133 seconds.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Sigmoid Activation 설명 없음

Similar Papers 제목 키워드 기반

Fast SDP certification of neural networks : towards large multi-class datasets

2026-07-03 · Margot Boyer, Clément Rambour, Zacharie Alès, Amélie Lambert arxiv

We present a new quadratic model for the certification problem in adversarial robustness, which simultaneously accounts for all possible target classes. Building on this model, we propose a novel semidefinite programming…

Adversarial Robustness

Fast Adversarial Robustness Certification of Nearest Prototype Classifiers for Arbitrary Seminorms

2020-12-01 · NeurIPS 2020 12 · Sascha Saralajew, Lars Holdijk, Thomas Villmann

Methods for adversarial robustness certification aim to provide an upper bound on the test error of a classifier under adversarial manipulation of its input. Current certification methods are computationally expensive an…

Adversarial RobustnessQuantizationTriplet

Incremental Randomized Smoothing Certification

2023-05-31 · Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh 외

Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method constructs a smoothed DNN model and certifie…

Halt Fast! Early Stopping for Certified Robustness

2026-06-26 · Andrew C. Cullen, Paul Montague, Benjamin I. P. Rubinstein arxiv

Randomized Smoothing (RS) provides rigorous robustness guarantees for neural networks without architectural constraints, yet its adoption is limited by extreme computational costs. Standard RS requires tens of thousands …

Certification of Speaker Recognition Models to Additive Perturbations

2024-04-29 · Dmitrii Korzh, Elvir Karimov, Mikhail Pautov, Oleg Y. Rogov 외

Speaker recognition technology is applied to various tasks, from personal virtual assistants to secure access systems. However, the robustness of these systems against adversarial attacks, particularly to additive pertur…

Few-Shot LearningSpeaker Recognition