Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks
The field of adversarial machine learning has experienced a near exponential growth in the amount of papers being produced since 2018. This massive information output has yet to be properly processed and categorized. In this paper, we seek to help alleviate this problem by systematizing the recent advances in adversarial machine learning black-box attacks since 2019. Our survey summarizes and categorizes 20 recent black-box attacks. We also present a new analysis for understanding the attack success rate with respect to the adversarial model used in each paper. Overall, our paper surveys a wide body of literature to highlight recent attack developments and organizes them into four attack categories: score based attacks, decision based attacks, transfer attacks and non-traditional attacks. Further, we provide a new mathematical framework to show exactly how attack results can fairly be compared.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningSimilar Papers 제목 키워드 기반
LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4
Automated theorem proving (ATP) has been a classical problem in artificial intelligence since its inception, yet it remains challenging due to its vast state and action space. Large language models (LLMs) have recently e…
Automated Theorem ProvingA Comparative Evaluation Methodology for NLG in Interactive Systems
Interactive systems have become an increasingly important type of application for deployment of NLG technology over recent years. At present, we do not yet have commonly agreed terminology or methodology for evaluating N…
Text GenerationPractical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms
Existing black-box attacks on deep neural networks (DNNs) have largely focused on transferability, where an adversarial instance generated for a locally trained model can âtransferâ to attack other learning models. I…
Exploring the Space of Black-box Attacks on Deep Neural Networks
Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models…
MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels
Large Language Models (LLMs) require robust confidence estimation, particularly in critical domains like healthcare and law where unreliable outputs can lead to significant consequences. Despite much recent work in confi…
Multiple-choiceText Generation