Search Results for author: Thai Le

Found 37 papers, 15 papers with code

Authorship Attribution for Neural Text Generation

no code implementations EMNLP 2020 Adaku Uchendu, Thai Le, Kai Shu, Dongwon Lee

In recent years, the task of generating realistic short and long texts have made tremendous advancements.

Authorship Attribution Text Generation

What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection

no code implementations23 May 2025 Binh Nguyen, Shuji Shi, Ryan Ofman, Thai Le

Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation.

Face Swapping text-to-speech +1

Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting

no code implementations22 May 2025 Bang Trinh Tran To, Thai Le

This work presents LURK (Latent UnleaRned Knowledge), a novel framework that probes for hidden retained knowledge in unlearned LLMs through adversarial suffix prompting.

Diagnostic

CAIN: Hijacking LLM-Humans Conversations via a Two-Stage Malicious System Prompt Generation and Refining Framework

no code implementations22 May 2025 Viet Pham, Thai Le

To demonstrate such an attack, we develop CAIN, an algorithm that can automatically curate such harmful system prompts for a specific target question in a black-box setting or without the need to access the LLM's parameters.

Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification

no code implementations20 May 2025 Tuc Nguyen, Yifan Hu, Thai Le

There are three major automated tasks in authorship privacy, namely authorship obfuscation (AO), authorship mimicking (AM), and authorship verification (AV).

Articles Authorship Verification

Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI

no code implementations3 Jan 2025 Christopher Burger, Charles Walter, Thai Le, Lingwei Chen

Recent work has investigated the concept of adversarial attacks on explainable AI (XAI) in the NLP domain with a focus on examining the vulnerability of local surrogate methods such as Lime to adversarial perturbations or small changes on the input of a machine learning (ML) model.

Adversarial Robustness

Natural Language Processing Methods for the Study of Protein-Ligand Interactions

no code implementations19 Sep 2024 James Michels, Ramya Bandarupalli, Amin Ahangar Akbari, Thai Le, Hong Xiao, Jing Li, Erik F. Y. Hom

Recent advances in Natural Language Processing (NLP) have ignited interest in developing effective methods for predicting protein-ligand interactions (PLIs) given their relevance to drug discovery and protein engineering efforts and the ever-growing volume of biochemical sequence and structural data available.

Drug Discovery

NoMatterXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models

no code implementations20 Aug 2024 Tuc Nguyen, James Michels, Hua Shen, Thai Le

In Explainable AI (XAI), counterfactual explanations (CEs) are a well-studied method to communicate feature relevance through contrastive reasoning of "what if" to explain AI models' predictions.

Attribute counterfactual +2

PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection

no code implementations24 Jun 2024 Jooyoung Lee, Toshini Agrawal, Adaku Uchendu, Thai Le, Jinghui Chen, Dongwon Lee

We then leverage our proposed dataset to evaluate the plagiarism detection performance of five modern LLMs and three specialized plagiarism checkers.

The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI

no code implementations22 Jun 2024 Christopher Burger, Charles Walter, Thai Le

Recent work has investigated the vulnerability of local surrogate methods to adversarial perturbations on a machine learning (ML) model's inputs, where the explanation is manipulated while the meaning and structure of the original input remains similar under the complex model.

Adversarial Attack

Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models

no code implementations22 Jun 2024 Christopher Burger, Yifan Hu, Thai Le

The location of knowledge within Generative Pre-trained Transformer (GPT)-like models has seen extensive recent investigation.

A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models

1 code implementation18 Feb 2024 Cuong Dang, Dung D. Le, Thai Le

First, empirical analyses show that (a) extracted features can be used with a lightweight classifier such as Random Forest to predict the attack success rate effectively, and (b) features with the most influence on the model robustness have a clear correlation with the robustness.

Adversarial Robustness Adversarial Text

Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning

no code implementations16 Feb 2024 Tuc Nguyen, Thai Le

Several parameter-efficient fine-tuning methods based on adapters have been proposed as a streamlined approach to incorporate not only a single specialized knowledge into existing Pre-Trained Language Models (PLMs) but also multiple of them at once.

Computational Efficiency parameter-efficient fine-tuning

ALISON: Fast and Effective Stylometric Authorship Obfuscation

1 code implementation1 Feb 2024 Eric Xing, Saranya Venkatraman, Thai Le, Dongwon Lee

AO is the corresponding adversarial task, aiming to modify a text in such a way that its semantics are preserved, yet an AA model cannot correctly infer its authorship.

Authorship Attribution

Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers

no code implementations18 Jan 2024 Tuc Nguyen, Thai Le

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their robustness under adversarial attacks.

Adversarial Robustness parameter-efficient fine-tuning +2

A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts

1 code implementation14 Nov 2023 Nafis Irtiza Tripto, Saranya Venkatraman, Dominik Macko, Robert Moro, Ivan Srba, Adaku Uchendu, Thai Le, Dongwon Lee

In the realm of text manipulation and linguistic transformation, the question of authorship has been a subject of fascination and philosophical inquiry.

text-classification Text Classification

MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark

1 code implementation20 Oct 2023 Dominik Macko, Robert Moro, Adaku Uchendu, Jason Samuel Lucas, Michiharu Yamashita, Matúš Pikuliak, Ivan Srba, Thai Le, Dongwon Lee, Jakub Simko, Maria Bielikova

There is a lack of research into capabilities of recent LLMs to generate convincing text in languages other than English and into performance of detectors of machine-generated text in multilingual settings.

Benchmarking de-en +1

TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles

1 code implementation22 Sep 2023 Adaku Uchendu, Thai Le, Dongwon Lee

We propose TopFormer to improve existing AA solutions by capturing more linguistic patterns in deepfake texts by including a Topological Data Analysis (TDA) layer in the Transformer-based model.

Authorship Attribution Face Swapping +3

Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack

1 code implementation21 May 2023 Christopher Burger, Lingwei Chen, Thai Le

LIME has emerged as one of the most commonly referenced tools in explainable AI (XAI) frameworks that is integrated into critical machine learning applications--e. g., healthcare and finance.

Adversarial Attack

Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?

2 code implementations3 Apr 2023 Adaku Uchendu, Jooyoung Lee, Hua Shen, Thai Le, Ting-Hao 'Kenneth' Huang, Dongwon Lee

Advances in Large Language Models (e. g., GPT-4, LLaMA) have improved the generation of coherent sentences resembling human writing on a large scale, resulting in the creation of so-called deepfake texts.

Face Swapping Human Detection +1

CRYPTEXT: Database and Interactive Toolkit of Human-Written Text Perturbations in the Wild

no code implementations16 Jan 2023 Thai Le, Ye Yiran, Yifan Hu, Dongwon Lee

CRYPTEXT is a data-intensive application that provides the users with a database and several tools to extract and interact with human-written perturbations.

Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective

no code implementations19 Oct 2022 Adaku Uchendu, Thai Le, Dongwon Lee

Two interlocking research questions of growing interest and importance in privacy research are Authorship Attribution (AA) and Authorship Obfuscation (AO).

Attribute Authorship Attribution +1

Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense

1 code implementation Findings (ACL) 2022 Thai Le, Jooyoung Lee, Kevin Yen, Yifan Hu, Dongwon Lee

We find that adversarial texts generated by ANTHRO achieve the best trade-off between (1) attack success rate, (2) semantic preservation of the original text, and (3) stealthiness--i. e. indistinguishable from human writings hence harder to be flagged as suspicious.

Adversarial Attack

Do Language Models Plagiarize?

1 code implementation15 Mar 2022 Jooyoung Lee, Thai Le, Jinghui Chen, Dongwon Lee

Our results suggest that (1) three types of plagiarism widely exist in LMs beyond memorization, (2) both size and decoding methods of LMs are strongly associated with the degrees of plagiarism they exhibit, and (3) fine-tuned LMs' plagiarism patterns vary based on their corpus similarity and homogeneity.

Language Modelling Memorization +1

Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning

no code implementations20 Oct 2021 Thai Le, Long Tran-Thanh, Dongwon Lee

To this question, we successfully demonstrate that indeed it is possible for adversaries to exploit computational learning mechanism such as reinforcement learning (RL) to maximize the influence of socialbots while avoiding being detected.

Adversarial Attack Hierarchical Reinforcement Learning +2

Large-Scale Data-Driven Airline Market Influence Maximization

no code implementations31 May 2021 Duanshun Li, Jing Liu, Jinsung Jeon, Seoyoung Hong, Thai Le, Dongwon Lee, Noseong Park

On top of the prediction models, we define a budget-constrained flight frequency optimization problem to maximize the market influence over 2, 262 routes.

Prediction

SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher

1 code implementation ACL 2022 Thai Le, Noseong Park, Dongwon Lee

Even though several methods have proposed to defend textual neural network (NN) models against black-box adversarial attacks, they often defend against a specific text perturbation strategy and/or require re-training the models from scratch.

Adversarial Robustness

MALCOM: Generating Malicious Comments to Attack Neural Fake News Detection Models

1 code implementation1 Sep 2020 Thai Le, Suhang Wang, Dongwon Lee

In recent years, the proliferation of so-called "fake news" has caused much disruptions in society and weakened the news ecosystem.

Articles Comment Generation +1

GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model's Prediction

1 code implementation5 Nov 2019 Thai Le, Suhang Wang, Dongwon Lee

Despite the recent development in the topic of explainable AI/ML for image and text data, the majority of current solutions are not suitable to explain the prediction of neural network models when the datasets are tabular and their features are in high-dimensional vectorized formats.

Philosophy

Machine Learning Based Detection of Clickbait Posts in Social Media

no code implementations5 Oct 2017 Xinyue Cao, Thai Le, Jason, Zhang

In this paper, we make use of a dataset from the clickbait challenge 2017 (clickbait-challenge. com) comprising of over 21, 000 headlines/titles, each of which is annotated by at least five judgments from crowdsourcing on how clickbait it is.

BIG-bench Machine Learning Clickbait Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.