Unrestricted Adversarial Examples
We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to unconstrained adversaries. Defenders submit machine learning models, and try to achieve high accuracy and coverage on non-adversarial data while making no confident mistakes on adversarial inputs. Attackers try to subvert defenses by finding arbitrary unambiguous inputs where the model assigns an incorrect label with high confidence. We propose a simple unambiguous dataset ("bird-or- bicycle") to use as part of this contest. We hope this contest will help to more comprehensively evaluate the worst-case adversarial risk of machine learning models.
Code (1)
Tasks
BIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Content-based Unrestricted Adversarial Attack
Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to de…
Adversarial AttackConstructing Unrestricted Adversarial Examples with Generative Models
Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose u…
Generative Adversarial NetworkAdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass …
Adversarial AttackAdversarial DefenseSynthesizing Unrestricted False Positive Adversarial Objects Using Generative Models
Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unres…
Objectobject-detectionObject DetectionGenerating Unrestricted Adversarial Examples via Three Parameters
Deep neural networks have been shown to be vulnerable to adversarial examples deliberately constructed to misclassify victim models. As most adversarial examples have restricted their perturbations to $L_{p}$-norm, exist…
Adversarial Attack