all InfoSec news
Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attribution Methods
May 7, 2024, 4:11 a.m. | Peiyu Yang, Naveed Akhtar, Jiantong Jiang, Ajmal Mian
cs.CR updates on arXiv.org arxiv.org
Abstract: Attribution methods compute importance scores for input features to explain the output predictions of deep models. However, accurate assessment of attribution methods is challenged by the lack of benchmark fidelity for attributing model predictions. Moreover, other confounding factors in attribution estimation, including the setup choices of post-processing techniques and explained model predictions, further compromise the reliability of the evaluation. In this work, we first identify a set of fidelity criteria that reliable benchmarks for attribution …
arxiv assessment attribution backdoor benchmark compute cs.ai cs.cr cs.lg evaluation explainable ai features fidelity high input predictions setup
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Senior - Penetration Tester
@ Deloitte | Madrid, España
Associate Cyber Incident Responder
@ Highmark Health | PA, Working at Home - Pennsylvania
Senior Insider Threat Analyst
@ IT Concepts Inc. | Woodlawn, Maryland, United States