all InfoSec news
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks. (arXiv:2206.08514v1 [cs.LG])
June 20, 2022, 1:20 a.m. | Ganqu Cui, Lifan Yuan, Bingxiang He, Yangyi Chen, Zhiyuan Liu, Maosong Sun
cs.CR updates on arXiv.org arxiv.org
Textual backdoor attacks are a kind of practical threat to NLP systems. By
injecting a backdoor in the training phase, the adversary could control model
predictions via predefined triggers. As various attack and defense models have
been proposed, it is of great significance to perform rigorous evaluations.
However, we highlight two issues in previous backdoor learning evaluations: (1)
The differences between real-world scenarios (e.g. releasing poisoned datasets
or models) are neglected, and we argue that each scenario has its own …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Azure Security Architect
@ First Quality | Remote US - Eastern or Central Timezone
Cyber Security Principal Consultant
@ Capco | New York City
Information Security Engineers
@ D. E. Shaw Research | New York City
Jr. Security Analyst
@ Alation, Inc. | Chennai
Cyber Security Systems Administrator
@ Crystal Dynamics | Remote - US
Senior Manufacturing IT Security Engineer
@ Bosch Group | Seberang Perai Selatan, Malaysia