A Note on Implementation Errors in Recent Adaptive Attacks Against Multi-Resolution Self-Ensembles
This note documents an implementation issue in recent adaptive attacks (Zhang et al. [2024]) against the multi-resolution self-ensemble defense (Fort and Lakshminarayanan [2024]). The implementation allowed adversarial perturbations to exceed the standard $L_\infty = 8/255$ bound by up to a factor of 20$\times$, reaching magnitudes of up to $L_\infty = 160/255$. When attacks are properly constrained within the intended bounds, the defense maintains non-trivial robustness. Beyond highlighting the importance of careful validation in adversarial machine learning research, our analysis reveals an intriguing finding: properly bounded adaptive attacks against strong multi-resolution self-ensembles often align with human perception, suggesting the need to reconsider how we measure adversarial robustness.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adaptive Nearest Neighbor Machine Translation
kNN-MT, recently proposed by Khandelwal et al. (2020a), successfully combines pre-trained neural machine translation (NMT) model with token-level k-nearest-neighbor (kNN) retrieval to improve the translation accuracy. Ho…
Machine TranslationNMTRetrievalTranslationRetriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) mitigates issues of the factual errors and hallucinated outputs generated by Large Language Models (LLMs) in open-domain question-answering tasks (OpenQA) via introducing external kno…
Open-Domain Question AnsweringQuestion AnsweringRAGRetrieval+1Buffer Zone based Defense against Adversarial Examples in Image Classification
Recent defenses published at venues like NIPS, ICML, ICLR and CVPR are mainly focused on mitigating white-box attacks. These defenses do not properly consider adaptive adversaries. In this paper, we expand the scope of t…
Adversarial RobustnessClassificationGeneral Classificationimage-classification+1Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output Codes
Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks. In this paper, we investigate the robustness of Er…
Adversarial RobustnessDiversityGeneralization Error Matters in Decentralized Learning Under Byzantine Attacks
Recently, decentralized learning has emerged as a popular peer-to-peer signal and information processing paradigm that enables model training across geographically distributed agents in a scalable manner, without the pre…