paper-with-me

홈 › Papers

Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes

2019-03-20 · NeurIPS 2019 12 · Matt Jordan, Justin Lewis, Alexandros G. Dimakis

We propose a novel method for computing exact pointwise robustness of deep neural networks for all convex $\ell_p$ norms. Our algorithm, GeoCert, finds the largest $\ell_p$ ball centered at an input point $x_0$, within which the output class of a given neural network with ReLU nonlinearities remains unchanged. We relate the problem of computing pointwise robustness of these networks to that of computing the maximum norm ball with a fixed center that can be contained in a non-convex polytope. This is a challenging problem in general, however we show that there exists an efficient algorithm to compute this for polyhedral complices. Further we show that piecewise linear neural networks partition the input space into a polyhedral complex. Our algorithm has the ability to almost immediately output a nontrivial lower bound to the pointwise robustness which is iteratively improved until it ultimately becomes tight. We empirically show that our approach generates distance lower bounds that are tighter compared to prior work, under moderate time constraints.

📄 PDF Abstract BibTeX arXiv:1903.08778

Code (1)

revbucket/geometric-certificates 공식 구현 pytorch

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…

Similar Papers 제목 키워드 기반

Certified but Fooled! Breaking Certified Defences with Ghost Certificates

2025-11-18 · Quoc Viet Vo, Tashreque M. Haq, Paul Montague, Tamas Abraham 외 arxiv

Certified defenses promise provable robustness guarantees. We study the malicious exploitation of probabilistic certification frameworks to better understand the limits of guarantee provisions. Now, the objective is to n…

Certifying Model Accuracy under Distribution Shifts

2022-01-28 · Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi

Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this work, we present provable robustness gu…

model

Provable Robustness for Streaming Models with a Sliding Window

2023-03-28 · Aounon Kumar, Vinu Sankar Sadasivan, Soheil Feizi

The literature on provable robustness in machine learning has primarily focused on static prediction problems, such as image classification, in which input samples are assumed to be independent and model performance is m…

Activity RecognitionHuman Activity Recognitionimage-classificationImage Classification

Projected Randomized Smoothing for Certified Adversarial Robustness

2023-09-25 · Samuel Pfrommer, Brendon G. Anderson, Somayeh Sojoudi

Randomized smoothing is the current state-of-the-art method for producing provably robust classifiers. While randomized smoothing typically yields robust $\ell_2$-ball certificates, recent research has generalized provab…

Adversarial Robustness

The Limitations of Adversarial Training and the Blind-Spot Attack

2019-01-15 · ICLR 2019 5 · Huan Zhang, Hongge Chen, Zhao Song, Duane Boning 외

The adversarial training procedure proposed by Madry et al. (2018) is one of the most effective methods to defend against adversarial examples in deep neural networks (DNNs). In our paper, we shed some lights on the prac…

valid