DeepAI AI Chat
Log In Sign Up

TMLab: Generative Enhanced Model (GEM) for adversarial attacks

by   Piotr Niewinski, et al.

We present our Generative Enhanced Model (GEM) that we used to create samples awarded the first prize on the FEVER 2.0 Breakers Task. GEM is the extended language model developed upon GPT-2 architecture. The addition of novel target vocabulary input to the already existing context input enabled controlled text generation. The training procedure resulted in creating a model that inherited the knowledge of pretrained GPT-2, and therefore was ready to generate natural-like English sentences in the task domain with some additional control. As a result, GEM generated malicious claims that mixed facts from various articles, so it became difficult to classify their truthfulness.


Neural Text Generation from Structured Data with Application to the Biography Domain

This paper introduces a neural model for concept-to-text generation that...

Multimodal Dialog Systems with Dual Knowledge-enhanced Generative Pretrained Language Model

Text response generation for multimodal task-oriented dialog systems, wh...

Large Scale Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training

Generating natural sentences from Knowledge Graph (KG) triples, known as...

Distributional Discrepancy: A Metric for Unconditional Text Generation

The goal of unconditional text generation is training a model with real ...

PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation

Existing work on controlled text generation (CTG) assumes a control inte...

Logically Consistent Adversarial Attacks for Soft Theorem Provers

Recent efforts within the AI community have yielded impressive results t...

Generating Label Cohesive and Well-Formed Adversarial Claims

Adversarial attacks reveal important vulnerabilities and flaws of traine...