Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ma, Qian, Ye, Ziping, Mehnaz, Shagufta
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2310.08808
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913022742626304
author Ma, Qian
Ye, Ziping
Mehnaz, Shagufta
author_facet Ma, Qian
Ye, Ziping
Mehnaz, Shagufta
contents To investigate the effectiveness of the model explanation in detecting adversarial examples, we reproduce the results of two papers, Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples and Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples. And then conduct experiments and case studies to identify the limitations of both works. We find that Attacks Meet Interpretability(AmI) is highly dependent on the selection of hyperparameters. Therefore, with a different hyperparameter choice, AmI is still able to detect Nicholas Carlini's attack. Finally, we propose recommendations for future work on the evaluation of defense techniques such as AmI.
format Preprint
id arxiv_https___arxiv_org_abs_2310_08808
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Attacks Meet Interpretability (AmI) Evaluation and Findings
Ma, Qian
Ye, Ziping
Mehnaz, Shagufta
Cryptography and Security
To investigate the effectiveness of the model explanation in detecting adversarial examples, we reproduce the results of two papers, Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples and Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples. And then conduct experiments and case studies to identify the limitations of both works. We find that Attacks Meet Interpretability(AmI) is highly dependent on the selection of hyperparameters. Therefore, with a different hyperparameter choice, AmI is still able to detect Nicholas Carlini's attack. Finally, we propose recommendations for future work on the evaluation of defense techniques such as AmI.
title Attacks Meet Interpretability (AmI) Evaluation and Findings
topic Cryptography and Security
url https://arxiv.org/abs/2310.08808