paper-with-me

Papers

Attack Transferability Characterization for Adversarially Robust Multi-label Classification

2021-06-29 · Zhuo Yang, Yufei Han, Xiangliang Zhang

Despite of the pervasive existence of multi-label evasion attack, it is an open yet essential problem to characterize the origin of the adversarial vulnerability of a multi-label learning system and assess its attackability. In this study, we focus on non-targeted evasion attack against multi-label classifiers. The goal of the threat is to cause miss-classification with respect to as many labels as possible, with the same input perturbation. Our work gains in-depth understanding about the multi-label adversarial attack by first characterizing the transferability of the attack based on the functional properties of the multi-label classifier. We unveil how the transferability level of the attack determines the attackability of the classifier via establishing an information-theoretic analysis of the adversarial risk. Furthermore, we propose a transferability-centered attackability assessment, named Soft Attackability Estimator (SAE), to evaluate the intrinsic vulnerability level of the targeted multi-label classifier. This estimator is then integrated as a transferability-tuning regularization term into the multi-label learning paradigm to achieve adversarially robust classification. The experimental study on real-world data echos the theoretical analysis and verify the validity of the transferability-regularized multi-label learning method.

📄 PDF Abstract BibTeX arXiv:2106.15360

Code (1)

chelungungun/Transferability_MLATTACK 공식 구현 tf

Tasks

Adversarial AttackClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label LearningRobust classification

Similar Papers 제목 키워드 기반

ARMOURED: Adversarially Robust MOdels using Unlabeled data by REgularizing Diversity

2021-01-01 · ICLR 2021 1 · Kangkang Lu, Cuong Manh Nguyen, Xun Xu, Kiran Chari 외

Adversarial attacks pose a major challenge for modern deep neural networks. Recent advancements show that adversarially robust generalization requires a huge amount of labeled data for training. If annotation becomes a b…

DiversityMULTI-VIEW LEARNINGPoint Processes

Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization

2025-02-04 · Yixiao Chen, Shikun Sun, Jianshu Li, Ruoyu Li 외

Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial. Existing generator-based attacks have excellent generalization and trans…

"What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models

2021-02-09 · Sahar Abdelnabi, Mario Fritz

Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. While numerous defenses aiming to improve …

Diversity

On the Transferability of Adversarial Examples between Encrypted Models

2022-09-07 · Miki Tanaka, Isao Echizen, Hitoshi Kiya

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, namely, AEs generated for a source model fool other (target) models. In this p…

image-classificationImage Classification

A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability

2022-02-11 · Idan Attias, Steve Hanneke, Yishay Mansour

We study the problem of learning an adversarially robust predictor to test time attacks in the semi-supervised PAC model. We address the question of how many labeled and unlabeled examples are required to ensure learning…

PAC learning