arXiv subjects

Amrita Bhattacharjee

Publications and source records attributed to Amrita Bhattacharjee.

27 records · Page 2Linked to original sources

arXiv2023

J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News

The rapid proliferation of AI-generated text online is profoundly reshaping the information landscape. Among various types of AI-generated text, AI-generated news presents a significant threat as it can be a prominent source of misinformation online. While several recent efforts have focused on detecting AI-generated text in general, these methods require enhanced reliability, given concerns about their vulnerability to simple adversarial attacks. Furthermore, due to the eccentricities of news writing, applying these detection methods for AI-generated news can produce false positives, potentially damaging the reputation of news organizations. To address these challenges, we leverage the expertise of an interdisciplinary team to develop a framework, J-Guard, capable of steering existing supervised AI text detectors for detecting AI-generated news while boosting adversarial robustness. By incorporating stylistic cues inspired by the unique journalistic attributes, J-Guard effectively distinguishes between real-world journalism and AI-generated news articles. Our experiments on news articles generated by a vast array of AI models, including ChatGPT (GPT3.5), demonstrate the effectiveness of J-Guard in enhancing detection capabilities while maintaining an average performance decrease of as low as 7% when faced with adversarial attacks.

cs.CL↗

arXiv2023

Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?

Large language models (LLMs) such as ChatGPT are increasingly being used for various use cases, including text content generation at scale. Although detection methods for such AI-generated text exist already, we investigate ChatGPT's performance as a detector on such AI-generated text, inspired by works that use ChatGPT as a data labeler or annotator. We evaluate the zero-shot performance of ChatGPT in the task of human-written vs. AI-generated text detection, and perform experiments on publicly available datasets. We empirically investigate if ChatGPT is symmetrically effective in detecting AI-generated or human-written text. Our findings provide insight on how ChatGPT and similar LLMs may be leveraged in automated detection pipelines by simply focusing on solving a specific aspect of the problem and deriving the rest from that solution. All code and data is available at https://github.com/AmritaBh/ChatGPT-as-Detector.

cs.CL↗

arXiv2023

Towards Detecting Harmful Agendas in News Articles

Manipulated news online is a growing problem which necessitates the use of automated systems to curtail its spread. We argue that while misinformation and disinformation detection have been studied, there has been a lack of investment in the important open challenge of detecting harmful agendas in news articles; identifying harmful agendas is critical to flag news campaigns with the greatest potential for real world harm. Moreover, due to real concerns around censorship, harmful agenda detectors must be interpretable to be effective. In this work, we propose this new task and release a dataset, NewsAgendas, of annotated news articles for agenda identification. We show how interpretable systems can be effective on this task and demonstrate that they can perform comparably to black-box models.

cs.CL↗

arXiv2023

Stylometric Detection of AI-Generated Text in Twitter Timelines

Recent advancements in pre-trained language models have enabled convenient methods for generating human-like text at a large scale. Though these generation capabilities hold great potential for breakthrough applications, it can also be a tool for an adversary to generate misinformation. In particular, social media platforms like Twitter are highly susceptible to AI-generated misinformation. A potential threat scenario is when an adversary hijacks a credible user account and incorporates a natural language generator to generate misinformation. Such threats necessitate automated detectors for AI-generated tweets in a given user's Twitter timeline. However, tweets are inherently short, thus making it difficult for current state-of-the-art pre-trained language model-based detectors to accurately detect at what point the AI starts to generate tweets in a given Twitter timeline. In this paper, we present a novel algorithm using stylometric signals to aid detecting AI-generated tweets. We propose models corresponding to quantifying stylistic changes in human and AI tweets in two related tasks: Task 1 - discriminate between human and AI-generated tweets, and Task 2 - detect if and when an AI starts to generate tweets in a given Twitter timeline. Our extensive experiments demonstrate that the stylometric features are effective in augmenting the state-of-the-art AI-generated text detectors.

cs.CL↗

arXiv2022

Reinforcement Learning Methods for Wordle: A POMDP/Adaptive Control Approach

In this paper we address the solution of the popular Wordle puzzle, using new reinforcement learning methods, which apply more generally to adaptive control of dynamic systems and to classes of Partially Observable Markov Decision Process (POMDP) problems. These methods are based on approximation in value space and the rollout approach, admit a straightforward implementation, and provide improved performance over various heuristic approaches. For the Wordle puzzle, they yield on-line solution strategies that are very close to optimal at relatively modest computational cost. Our methods are viable for more complex versions of Wordle and related search problems, for which an optimal strategy would be impossible to compute. They are also applicable to a wide range of adaptive sequential decision problems that involve an unknown or frequently changing environment whose parameters are estimated on-line.

cs.AI↗

arXiv2022

Text Transformations in Contrastive Self-Supervised Learning: A Review

Contrastive self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain of Natural Language Processing (NLP), the augmentation methods used in creating similar pairs with regard to contrastive learning (CL) assumptions are challenging. This is because, even simply modifying a word in the input might change the semantic meaning of the sentence, and hence, would violate the distributional hypothesis. In this review paper, we formalize the contrastive learning framework, emphasize the considerations that need to be addressed in the data transformation step, and review the state-of-the-art methods and evaluations for contrastive representation learning in NLP. Finally, we describe some challenges and potential directions for learning better text representations using contrastive methods.

cs.CL↗

arXiv2020

Disinformation in the Online Information Ecosystem: Detection, Mitigation and Challenges

With the rapid increase in access to internet and the subsequent growth in the population of online social media users, the quality of information posted, disseminated and consumed via these platforms is an issue of growing concern. A large fraction of the common public turn to social media platforms and in general the internet for news and even information regarding highly concerning issues such as COVID-19 symptoms. Given that the online information ecosystem is extremely noisy, fraught with misinformation and disinformation, and often contaminated by malicious agents spreading propaganda, identifying genuine and good quality information from disinformation is a challenging task for humans. In this regard, there is a significant amount of ongoing research in the directions of disinformation detection and mitigation. In this survey, we discuss the online disinformation problem, focusing on the recent 'infodemic' in the wake of the coronavirus pandemic. We then proceed to discuss the inherent challenges in disinformation research, and then elaborate on the computational and interdisciplinary approaches towards mitigation of disinformation, after a short overview of the various directions explored in detection efforts.

cs.SI↗

arXiv2020

Combating Disinformation in a Social Media Age

The creation, dissemination, and consumption of disinformation and fabricated content on social media is a growing concern, especially with the ease of access to such sources, and the lack of awareness of the existence of such false information. In this paper, we present an overview of the techniques explored to date for the combating of disinformation with various forms. We introduce different forms of disinformation, discuss factors related to the spread of disinformation, elaborate on the inherent challenges in detecting disinformation, and show some approaches to mitigating disinformation via education, research, and collaboration. Looking ahead, we present some promising future research directions on disinformation.

cs.SI↗

arXiv2020

Challenges in Combating COVID-19 Infodemic -- Data, Tools, and Ethics

While the COVID-19 pandemic continues its global devastation, numerous accompanying challenges emerge. One important challenge we face is to efficiently and effectively use recently gathered data and find computational tools to combat the COVID-19 infodemic, a typical information overloading problem. Novel coronavirus presents many questions without ready answers; its uncertainty and our eagerness in search of solutions offer a fertile environment for infodemic. It is thus necessary to combat the infodemic and make a concerted effort to confront COVID-19 and mitigate its negative impact in all walks of life when saving lives and maintaining normal orders during trying times. In this position paper of combating the COVID-19 infodemic, we illustrate its need by providing real-world examples of rampant conspiracy theories, misinformation, and various types of scams that take advantage of human kindness, fear, and ignorance. We present three key challenges in this fight against the COVID-19 infodemic where researchers and practitioners instinctively want to contribute and help. We demonstrate that these three challenges can and will be effectively addressed by collective wisdom, crowdsourcing, and collaborative research.

cs.SI↗