Protect Theft How To Yourself Against Identity Protect Theft How To Yourself Against Identity
Alastair Douglas, CEO of Totally Money, advises on what to look out for and how to protect your ID to avoid being scammedHow to protect yourself against identity theft

Attention Users: at 8AM ET / 12PM UTC on Friday, June 21, the submission system will be unavailable for approximately 30 minutes for routine maintenance.

We gratefully acknowledge support from
Protect Theft How To Yourself Against
the Simons Foundation and member institutions.
Protect Theft How To Yourself Against Abstract: Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that closely mimics the style of real news.
Modern computer security relies on careful threat modeling: identifying potential threats and vulnerabilities from an adversary's point of view, and exploring potential mitigations to these threats. Likewise, developing robust defenses against neural fake news requires us first to carefully investigate and characterize the risks of these models. We thus present a model for controllable text generation called Grover. Given a headline like `Link Found Between Vaccines and Autism,' Grover can generate the rest of the article; humans find these generations to be more trustworthy than human-written disinformation.
Developing robust verification techniques against generators like Grover is critical. We find that best current discriminators can classify neural fake news from real, human-written, news with 73% accuracy, assuming access to a moderate level of training data. Counterintuitively, the best defense against Grover turns out to be Grover itself, with 92% accuracy, demonstrating the importance of public release of strong generators. We investigate these results further, showing that exposure bias -- and sampling strategies that alleviate its effects -- both leave artifacts that similar discriminators can pick up on. We conclude by discussing ethical issues regarding the technology, and plan to release Grover publicly, helping pave the way for better detection of neural fake news.
Untitled Document Untitled Document Untitled Untitled Document Untitled Document Document Document Untitled
Comments: this https URL
Protect Theft How To Yourself Against Subjects: Computation and Language (cs.CL); Computers and Society (cs.CY)
Cite as: arXiv:1905.12616 [cs.CL]
  (or arXiv:1905.12616v1 [cs.CL] for this version)
Try the Bibliographic Explorer
(can be disabled at any time)

Bibliographic data

Submission history

From: Rowan Zellers [ view email]
[v1] Wed, 29 May 2019 17:58:52 UTC (864 KB)
Record Accounts gov Bmv Searches In
Protect Theft How To Yourself Against