all InfoSec news
Attacks Meet Interpretability (AmI) Evaluation and Findings. (arXiv:2310.08808v1 [cs.CR])
cs.CR updates on arXiv.org arxiv.org
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. …
adversarial ami attacks case case studies detection evaluation findings identify limitations papers results studies