Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples?

No.

Security & robustness Software engineering cs.LG cs.AI cs.CR stat.ML Adversarial Robustness in Machine Learning Advanced Malware Detection Techniques Security and Verification in Computing Computer Science Mathematics

Paper

References (3)

01Attacks Meet Interpretability: Attribute-steered Detection of Adversarial SamplesGuanhong Tao, Shiqing Ma, Yingqi Liu et al.2018 · Neural Information Processing Systems · 168 citations In Library

02Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection MethodsNicholas Carlini, D. Wagner2017 · AISec@CCS · 2.0k citations In Library

03Intriguing properties of neural networksChristian Szegedy, Wojciech Zaremba, I. Sutskever et al.2013 · International Conference on Learning Representations · 17k citations In Library

Similar papers

Attacks Meet Interpretability (AmI) Evaluation and FindingsQian Ma, Ziping Ye, Shagufta Mehnaz2023 · arXiv (Cornell University) In Library

Enhancing Adversarial Example Detection Through Model ExplanationQian Ma, Ziping Ye2025 · arXiv (Cornell University) · 0 citations In Library

Adversarial Examples Are Not Real FeaturesAng Li, Yifei Wang, Yiwen Guo et al.2023 · arXiv (Cornell University) · 24 citations In Library

Analyzing the Impact of Adversarial Examples on Explainable Machine LearningPrathyusha Devabhakthini, Suvendu Chandan Nayak, Raj Shukla et al.2025 In Library

Attack as Defense: Characterizing Adversarial Examples using RobustnessZhe Zhao, Guangke Chen, Jingyi Wang et al.2021 · arXiv (Cornell University) · 36 citations In Library

Attack as defense: characterizing adversarial examples using robustnessZhe Zhao, Guangke Chen, Jingyi Wang et al.2021 In Library

On Evaluating Adversarial RobustnessNicholas Carlini, Anish Athalye, Nicolas Papernot et al.2019 · arXiv (Cornell University) · 1.0k citations In Library

Synthesizing Robust Adversarial ExamplesAnish Athalye, Logan Engstrom, Andrew Ilyas et al.2017 · International Conference on Machine Learning · 1.9k citations In Library

MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial ExamplesNicholas Carlini, David Wagner2017 · arXiv (Cornell University) · 257 citations In Library

Robust Feature-Level Adversaries are Interpretability ToolsStephen Casper, Max Nadeau, Dylan Hadfield-Menell et al.2021 · arXiv (Cornell University) · 34 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal