ACAnshuman Chhabra

Anshuman Chhabra

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Anshuman Chhabra has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers
    Open Access

    Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

    by Anshuman Chhabra, Shrestha Datta, Shahriar Kabir Nahin, Prasant Mohapatra

    Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web, software, and physical environments creates new and amplified security risks, distinct from both traditional AI safety and conventional software security. This survey outlines a taxonomy of threats specific to agentic AI, reviews recent benchmarks and evaluation methodologies, and discusses defense strategies from both technical and governance perspectives.We synthesize current research and highlight open challenges, aiming to support the development of secure-by-design agent systems.


  • Open Access

    Classification of Communication and Head Movement Behaviors during Multi-Person Conversations using Deep Learning

    by A Earley, A Chhabra, Ej Ozmeral, A Lertpoompunya, DA Eddins, Nc Higgins

    Head movements play a pivotal role while engaged in multi-talker conversation by providing non-verbal feedback to partners and enhancing a listener’s ability to separate sound sources. Commercial hearing-aids with an on-board IMU (Inertial Measurement Unit, i.e., accelerometers) typically use that information for step-counting and activity levels. At least one device uses it as an input to their environment classifier and integrated directional microphone. None, however, use the IMU to detect specific patterns of head movements to predict behaviors such as nodding, head shaking, listening to a person versus a video, or talking. Training an automatic classifier to accurately detect these behaviors first requires collecting head movement data during multi-person conversation and laboriously annotating each behavior-type for each participant with high temporal precision. From that point, with the goal of training the most accurate model and integrating with the hardware in the hearing aid to improve device performance, the question is how best to model the data. To address this gap, we collected accelerometer data during natural multi-person conversations and paired it with detailed human annotations of communication and head-movement behaviors. Head-movement data was collected from three cohorts of young, normal-hearing individuals (three per cohort) in a controlled, conference-room setting during 50-minute multi-talker conversations. Participants wore hearing aids with on-board accelerometers, and audio-video was recorded for each talker. Videos were manually annotated for communication and head-movement behaviors, including conversational turns and nonverbal cues such as tilts and nods. Temporal and spectral features were extracted from the accelerometer data (windowed into 1-second segments) corresponding to roll and pitch movements. These features, combined with the annotated behaviors, were used to train and test machine learning models. Models were trained on data from all but one participant and then tested on the held-out participant, repeating this procedure across all individuals. Several deep learning and classical machine learning models were compared for classifying communication behaviors (e.g., talking, listening, watching video) and head orientations (e.g., turning left or right, facing down, facing forward). More specifically, various sequence-to-sequence models, a state-of-the-art deep learning technique, were utilized. These models incorporated modern architectural components such as transformer networks. Multiple performance metrics were used to evaluate models, and results suggest that modern deep learning models outperform classical machine learning methods by significant margins. Classification performance improved further when temporal sequence information was incorporated. These results indicate that during multi-talker conversation, hearing-aid accelerometers can automatically classify stereotypical behaviors with high temporal resolution (1-second). Even when tested on unseen subjects, the models remained reliable. This establishes a foundation for more advanced approaches that combine behavioral and movement patterns, further integrate temporal dynamics, and incorporate additional inputs to improve accuracy and ecological validity.

  • Open Access

    Incentivizing news consumption on social media platforms using large language models and realistic bot accounts

    by Hadi Askari, Anshuman Chhabra, Bernhard Clemm von Hohenberg, Michael Heseltine, Magdalena Wojcieszak

    Polarization, misinformation, declining trust, and wavering support for democratic norms are pressing threats to the US Exposure to verified and balanced news may make citizens more resilient to these threats. This project examines how to enhance users’ exposure to and engagement with verified and ideologically balanced news in an ecologically valid setting. We rely on a 2-week long field experiment on 28,457 Twitter users. We created 28 bots utilizing GPT-2 that replied to users tweeting about sports, entertainment, or lifestyle with a contextual reply containing a URL to the topic-relevant section of a verified and ideologically balanced news organization and an encouragement to follow its Twitter account. To test differential effects by gender of the bots, the treated users were randomly assigned to receive responses by bots presented as female or male. We examine whether our intervention enhances the following of news media organizations, sharing and liking of news content (determined by our extensive list of news media outlets), tweeting about politics, and liking of political content (determined using our fine-tuned RoBERTa NLP transformer-based model). Although the treated users followed more news accounts and the users in the female bot treatment liked more news content than the control, these results were small in magnitude and confined to the already politically interested users, as indicated by their pretreatment tweeting about politics. In addition, the effects on liking and posting political content were uniformly null. These findings have implications for social media and news organizations and offer directions for pro-social computational interventions on platforms.


  • Open Access

    Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias

    by Anshuman Chhabra, Hadi Askari, Prasant Mohapatra

    We characterize and study zero-shot abstractive summarization in Large Language Models (LLMs) by measuring position bias, which we propose as a general formulation of the more restrictive lead bias phenomenon studied previously in the literature. Position bias captures the tendency of a model unfairly prioritizing information from certain parts of the input text over others, leading to undesirable behavior. Through numerous experiments on four diverse real-world datasets, we study position bias in multiple LLM models such as GPT 3.5-Turbo, Llama-2, and Dolly-v2, as well as state-of-the-art pretrained encoder-decoder abstractive summarization models such as Pegasus and BART. Our findings lead to novel insights and discussion on performance and position bias of models for zero-shot summarization tasks.


  • Open Access

    Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias

    by Anshuman Chhabra, Hadi Askari, Prasant Mohapatra

    Anshuman Chhabra, Hadi Askari, Prasant Mohapatra. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers). 2024.


  • Top Cited Papers
    Open Access

    Auditing YouTube’s recommendation system for ideologically congenial, extreme, and problematic recommendations

    by Muhammad Haroon, Magdalena Wojcieszak, Anshuman Chhabra, Xin Liu, Prasant Mohapatra, Zubair Shafiq

    Algorithms of social media platforms are often criticized for recommending ideologically congenial and radical content to their users. Despite these concerns, evidence on such filter bubbles and rabbit holes of radicalization is inconclusive. We conduct an audit of the platform using 100,000 sock puppets that allow us to systematically and at scale isolate the influence of the algorithm in recommendations. We test 1) whether recommended videos are congenial with regard to users’ ideology, especially deeper in the watch trail and whether 2) recommendations deeper in the trail become progressively more extreme and come from problematic channels. We find that YouTube’s algorithm recommends congenial content to its partisan users, although some moderate and cross-cutting exposure is possible and that congenial recommendations increase deeper in the trail for right-leaning users. We do not find meaningful increases in ideological extremity of recommendations deeper in the trail, yet we show that a growing proportion of recommendations comes from channels categorized as problematic (e.g., “IDW,” “Alt-right,” “Conspiracy,” and “QAnon”), with this increase being most pronounced among the very-right users. Although the proportion of these problematic recommendations is low (max of 2.5%), they are still encountered by over 36.1% of users and up to 40% in the case of very-right users.


  • Open Access

    Fair Algorithms for Hierarchical Agglomerative Clustering

    by Anshuman Chhabra, Prasant Mohapatra

    Hierarchical Agglomerative Clustering (HAC) algorithms are extensively utilized in modern data science, and seek to partition the dataset into clusters while generating a hierarchical relationship between the data samples. HAC algorithms are employed in many applications, such as biology, natural language processing, and recommender systems. Thus, it is imperative to ensure that these algorithms are fair -- even if the dataset contains biases against certain protected groups, the cluster outputs generated should not discriminate against samples from any of these groups. However, recent work in clustering fairness has mostly focused on center-based clustering algorithms, such as k-median and k-means clustering. In this paper, we propose fair algorithms for performing HAC that enforce fairness constraints 1) irrespective of the distance linkage criteria used, 2) generalize to any natural measures of clustering fairness for HAC, 3) work for multiple protected groups, and 4) have competitive running times to vanilla HAC. Through extensive experiments on multiple real-world UCI datasets, we show that our proposed algorithm finds fairer clusterings compared to vanilla HAC as well as other state-of-the-art fair clustering approaches.

  • Open Access

    Robust Fair Clustering: A Novel Fairness Attack and Defense Framework

    by Anshuman Chhabra, Peizhao Li, Prasant Mohapatra, Hongfu Liu

    Clustering algorithms are widely used in many societal resource allocation applications, such as loan approvals and candidate recruitment, among others, and hence, biased or unfair model outputs can adversely impact individuals that rely on these applications. To this end, many fair clustering approaches have been recently proposed to counteract this issue. Due to the potential for significant harm, it is essential to ensure that fair clustering algorithms provide consistently fair outputs even under adversarial influence. However, fair clustering algorithms have not been studied from an adversarial attack perspective. In contrast to previous research, we seek to bridge this gap and conduct a robustness analysis against fair clustering by proposing a novel black-box fairness attack. Through comprehensive experiments, we find that state-of-the-art models are highly susceptible to our attack as it can reduce their fairness performance significantly. Finally, we propose Consensus Fair Clustering (CFC), the first robust fair clustering approach that transforms consensus clustering into a fair graph partitioning problem, and iteratively learns to generate fair cluster outputs. Experimentally, we observe that CFC is highly robust to the proposed attack and is thus a truly robust fair clustering alternative.

  • Open Access

    Fair Clustering Using Antidote Data

    by Anshuman Chhabra, Adish Singla, Prasant Mohapatra

    Clustering algorithms are widely utilized for many modern data science applications. This motivates the need to make outputs of clustering algorithms fair. Traditionally, new fair algorithmic variants to clustering algorithms are developed for specific notions of fairness. However, depending on the application context, different definitions of fairness might need to be employed. As a result, new algorithms and analysis need to be proposed for each combination of clustering algorithm and fairness definition. Additionally, each new algorithm would need to be reimplemented for deployment in a real-world system. Hence, we propose an alternate approach to group-level fairness in center-based clustering inspired by research on data poisoning attacks. We seek to augment the original dataset with a small number of data points, called antidote data. When clustering is undertaken on this new dataset, the output is fair, for the chosen clustering algorithm and fairness definition. We formulate this as a general bi-level optimization problem which can accommodate any center-based clustering algorithms and fairness notions. We then categorize approaches for solving this bi-level optimization for two different problem settings. Extensive experiments on different clustering algorithms and fairness notions show that our algorithms can achieve desired levels of fairness on many real-world datasets with a very small percentage of antidote data added. We also find that our algorithms achieve lower fairness costs and competitive clustering performance compared to other state-of-the-art fair clustering algorithms.

  • Open Access

    An Overview of Fairness in Clustering

    by Anshuman Chhabra, Karina Masalkovaite, Prasant Mohapatra

    Clustering algorithms are a class of unsupervised machine learning (ML) algorithms that feature ubiquitously in modern data science, and play a key role in many learning-based application pipelines. Recently, research in the ML community has pivoted to analyzing the fairness of learning models, including clustering algorithms. Furthermore, research on fair clustering varies widely depending on the choice of clustering algorithm, fairness definitions employed, and other assumptions made regarding models. Despite this, a comprehensive survey of the field does not exist. In this paper, we seek to bridge this gap by categorizing existing research on fair clustering, and discussing possible avenues for future work. Through this survey, we aim to provide researchers with an organized overview of the field, and motivate new and unexplored lines of research regarding fairness in clustering.