Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script
DNN-based language models perform excellently on various tasks, but even SOTA LLMs are susceptible to textual adversarial attacks. Adversarial texts play crucial roles in multiple subfields of NLP. However, current research has the following issues. (1) Most textual adversarial attack methods target rich-resourced languages. How do we generate adversarial texts for less-studied languages? (2) Most textual adversarial attack methods are prone to generating invalid or ambiguous adversarial texts. How do we construct high-quality adversarial robustness benchmarks? (3) New language models may be immune to part of previously generated adversarial texts. How do we update adversarial robustness benchmarks? To address the above issues, we introduce HITL-GAT, a system based on a general approach to human-in-the-loop generation of adversarial texts. HITL-GAT contains four stages in one pipeline: victim model construction, adversarial example generation, high-quality benchmark construction, and adversarial robustness evaluation. Additionally, we utilize HITL-GAT to make a case study on Tibetan script which can be a reference for the adversarial research of other less-studied languages.
Code (1)
Tasks
Adversarial AttackAdversarial RobustnessSimilar Papers 제목 키워드 기반
Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering
Adversarial evaluation stress tests a model's understanding of natural language. While past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose h…
DiversityInformation RetrievalQuestion AnsweringRetrievalGraded Suspiciousness of Adversarial Texts to Human
Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, ho…
Adversarial AttackAdversarial TextSemantic SimilaritySemantic Textual Similarity+1Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation
Despite recent progress, state-of-the-art question answering models remain vulnerable to a variety of adversarial attacks. While dynamic adversarial data collection, in which a human annotator tries to write examples tha…
Answer SelectionQuestion AnsweringQuestion GenerationGenerating Natural Language Adversarial Examples on a Large Scale with Generative Models
Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise …
Adversarial TextGeneral ClassificationSentiment Analysistext-classification+2Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles
Autonomous vehicles in interactive traffic environments are often limited by the scarcity of safety-critical tail events in static datasets, which biases learned policies toward average-case behaviors and reduces robustn…
Autonomous Vehicles