paper-with-me

홈 › Papers

Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script

2024-12-17 · Xi Cao, Yuan Sun, Jiajun Li, Quzong Gesang, Nuo Qun, Tashi Nyima

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.

📄 PDF Abstract BibTeX arXiv:2412.12478

Code (1)

CMLI-NLP/HITL-GAT 공식 구현 pytorch

Tasks

Adversarial AttackAdversarial Robustness

Similar Papers 제목 키워드 기반

Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering

2018-09-07 · TACL 2019 3 · Eric Wallace, Pedro Rodriguez, Shi Feng, Ikuya Yamada 외

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 AnsweringRetrieval

Graded Suspiciousness of Adversarial Texts to Human

2024-10-06 · Shakila Mahjabin Tonni, Pedro Faustini, Mark Dras

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+1

Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation

2021-04-18 · EMNLP 2021 11 · Max Bartolo, Tristan Thrush, Robin Jia, Sebastian Riedel 외

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 Generation

Generating Natural Language Adversarial Examples on a Large Scale with Generative Models

2020-03-10 · Yankun Ren, Jianbin Lin, Siliang Tang, Jun Zhou 외

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+2

Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles

2026-04-08 · Yicheng Guo, Jiaqi Liu, Chengkai Xu, Peng Hang 외 arxiv

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