Search Results for author:
Found 37 papers, 15 papers with code
Detecting False Claims in Low-Resource Regions: A Case Study of Caribbean Islands
The COVID-19 pandemic has created threats to global health control.
Authorship Attribution for Neural Text Generation
In recent years, the task of generating realistic short and long texts have made tremendous advancements.
What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation.
Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting
This work presents LURK (Latent UnleaRned Knowledge), a novel framework that probes for hidden retained knowledge in unlearned LLMs through adversarial suffix prompting.
CAIN: Hijacking LLM-Humans Conversations via a Two-Stage Malicious System Prompt Generation and Refining Framework
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
There are three major automated tasks in authorship privacy, namely authorship obfuscation (AO), authorship mimicking (AM), and authorship verification (AV).
Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI
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.
xSRL: Safety-Aware Explainable Reinforcement Learning -- Safety as a Product of Explainability
This makes trust in the safety mechanisms of RL systems crucial for effective deployment.
Unveiling Topological Structures in Text: A Comprehensive Survey of Topological Data Analysis Applications in NLP
We conclude by exploring the challenges and unresolved questions that persist in this niche field.
Natural Language Processing Methods for the Study of Protein-Ligand Interactions
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.
NoMatterXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models
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.
PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection
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
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.
Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models
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
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.
Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning
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.
ALISON: Fast and Effective Stylometric Authorship Obfuscation
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.
Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers
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.
A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts
In the realm of text manipulation and linguistic transformation, the question of authorship has been a subject of fascination and philosophical inquiry.
HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis
Thus, we introduce the largest benchmark for spoken texts - HANSEN (Human ANd ai Spoken tExt beNchmark).
MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
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.
TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles
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.
Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial Attack
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.
Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?
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.
NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models
Online texts with toxic content are a clear threat to the users on social media in particular and society in general.
CRYPTEXT: Database and Interactive Toolkit of Human-Written Text Perturbations in the Wild
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
Two interlocking research questions of growing interest and importance in privacy research are Authorship Attribution (AA) and Authorship Obfuscation (AO).
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense
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.
Do Language Models Plagiarize?
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.
Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning
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.
TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation
Recent progress in generative language models has enabled machines to generate astonishingly realistic texts.
Large-Scale Data-Driven Airline Market Influence Maximization
On top of the prediction models, we define a budget-constrained flight frequency optimization problem to maximize the market influence over 2, 262 routes.
A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attacks
The Universal Trigger (UniTrigger) is a recently-proposed powerful adversarial textual attack method.
SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher
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.
MALCOM: Generating Malicious Comments to Attack Neural Fake News Detection Models
In recent years, the proliferation of so-called "fake news" has caused much disruptions in society and weakened the news ecosystem.
GRACE: Generating Concise and Informative Contrastive Sample to Explain Neural Network Model's Prediction
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.
Machine Learning Based Detection of Clickbait Posts in Social Media
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.
