Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples

2023-02-09 · Andrew C. Cullen, Shijie Liu, Paul Montague, Sarah M. Erfani, Benjamin I. P. Rubinstein

In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications can compromise the very models they help to protect? Our new \emph{Certification Aware Attack} exploits certifications to produce computationally efficient norm-minimising adversarial examples $74 \%$ more often than comparable attacks, while reducing the median perturbation norm by more than $10\%$. While these attacks can be used to assess the tightness of certification bounds, they also highlight that releasing certifications can paradoxically reduce security.

📄 PDF Abstract BibTeX arXiv:2302.04379

Code (1)

andrew-cullen/attacking-certified-robustness 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity

2022-10-12 · Andrew C. Cullen, Paul Montague, Shijie Liu, Sarah M. Erfani 외

In response to subtle adversarial examples flipping classifications of neural network models, recent research has promoted certified robustness as a solution. There, invariance of predictions to all norm-bounded attacks …

Open-Ended Question Answering

Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications

2026-06-22 · Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris, João Marques-Silva arxiv

A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify. To mitigate this problem, recent research focuses on the computation…

$\ell_1$ Adversarial Robustness Certificates: a Randomized Smoothing Approach

2019-09-25 · Jiaye Teng, Guang-He Lee, Yang Yuan

Robustness is an important property to guarantee the security of machine learning models. It has recently been demonstrated that strong robustness certificates can be obtained on ensemble classifiers generated by input r…

Adversarial Robustness

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…

Higher-Order Certified Robustness for Regression

2026-07-06 · Jie Zhang, Natalie Frank arxiv

Randomized smoothing has emerged as a scalable technique for certifying the adversarial robustness of classifiers. However, its application to regression remains under-explored and faces unique challenges. Existing regre…