Publications 📄

Preprints:

• Exposing the Illusion of Erasure in Knowledge Editing for LLMs [PDF]
  A.R. Basani, A. Chhabra
  
  

• SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening [PDF]
  S.K. Nahin, H. Askari, M. Chen, A. Chhabra
  
  

• Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling [PDF]
  O. Monjur, S.K. Nahin, A. Chhabra
  
  

• AfriLangTutor: Advancing Language Tutoring and Culture Education in Low-Resource Languages with LLMs [PDF]
  T.D. Belay, S.K. Nahin, I.A. Azime, O. Monjur, S.H. Muhammad, S.M. Yimam, A. Chhabra
  
  

• Golden Layers and Where to Find Them: Improved Knowledge Editing for LLMs Via Layer Gradient Analysis [PDF]
  S. Datta, H. Liu, A. Chhabra
  
  

• What Is The Performance Ceiling of My Classifier? Utilizing Category-Wise Influence Functions for Pareto Frontier Analysis [PDF]
  S.K. Nahin, W. Xiao, J. Liu, A. Chhabra, H. Liu
  
  

• Towards Safer Social Media Platforms: Scalable and Performant Few-Shot Harmful Content Moderation Using LLMs [PDF]
  A. Bonagiri, L. Li, R. Oak, Z. Babar, M. Wojcieszak, A. Chhabra
  
  

• Unraveling Indirect In-Context Learning Using Influence Functions [PDF]
  H. Askari, S. Gupta, T. Tong, F. Wang, A. Chhabra, M. Chen

Publications:

• Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models,
  ICML (2026) [PDF]
  S.K. Nahin, H. Askari, M. Chen, A. Chhabra
  
  

• First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation,
  ICLR (2026) [PDF]
  D. Vitel, A. Chhabra
  
  

• Bridging the Culture Gap: A Framework for LLM-Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages,
  ACL - Findings (2026) [PDF]
  I.A. Azime, T.D. Belay, D. Klakow, P. Slusallek, A. Chhabra
  
  

• Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges,
  IEEE Access (2026) [PDF]
  A. Chhabra, S. Datta, S.K. Nahin, P. Mohapatra
  
  

• Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive LLM Optimization,
  UAI (2026) [PDF]
  T. Amaefuna, H. Vaidya, A. Chhabra, A. Mali
  
  

• User-Side Interventions Reduce Harmful Content Exposure in Algorithmic Feeds,
  ICWSM (2026) [PDF]
  L. Li, A. Chhabra, M. Wojcieszak
  
  

• LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions,
  NeurIPS (2025) [PDF]
  H. Askari, S. Gupta, F. Wang, A. Chhabra, M. Chen
  
  

• Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models,
  ICML (2025) - Oral [PDF]
  A. Chhabra,  B. Li, J. Chen, P. Mohapatra, H. Liu
  
  

• Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms,
  ACL (2025) - Oral [PDF]
  R. Oak, M. Haroon, C. Jo, M. Wojcieszak, A. Chhabra
  
  

• Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers,
  NAACL (2025) - Oral [PDF]
  A. Achara, A. Chhabra
  
  

• Assessing LLMs For Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing,
  NAACL - Findings (2025) [PDF]
  H. Askari, A. Chhabra, M. Chen, P. Mohapatra
  
  

• "Whose Side Are You On?" Estimating Ideology of Political and News Content Using LLMs and Few-shot Demonstration Selection
  AACL - Findings (2025) [PDF]
  M. Haroon, M. Wojcieszak, A. Chhabra
  
  

• From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Models
  AACL (2025) [PDF]
  M. Kamruzzaman, A. Monsur, G. Kim, A. Chhabra
  
  

• Incentivizing News Consumption on Social Media Platforms Using Large Language Models and Realistic Bot Accounts,
  PNAS Nexus (2024) [PDF]
  H. Askari, A. Chhabra, B. Hohenberg, M. Heseltine, M. Wojcieszak
  
  

• Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias,
  NAACL (2024) - Oral [PDF]
  A. Chhabra, H. Askari, P. Mohapatra
  
  

• “What Data Benefits My Classifier?” Enhancing Model Performance and Interpretability Through Influence-Based Data Selection,
  ICLR (2024) - Oral [PDF]
  A. Chhabra, P. Li, P. Mohapatra, H. Liu
  
  

• Towards Fair Video Summarization,
  TMLR (2023) [PDF]
  A. Chhabra, K. Patwari, C. Kuntala, Sristi, D.K. Sharma, P. Mohapatra
  
  

• Robust Fair Clustering: A Novel Fairness Attack and Defense Framework,
  ICLR (2023) [PDF]
  A. Chhabra, P. Li, P. Mohapatra, H. Liu
  
  

• On the Robustness of Deep Clustering Models: Attacks and Defenses,
  NeurIPS (2022) [PDF]
  A. Chhabra, A. Sekhari, P. Mohapatra
  
  

• Suspicion-Free Adversarial Attacks on Clustering Algorithms,
  AAAI (2020) [PDF]
  A. Chhabra, A. Roy, P. Mohapatra
  
  

• Auditing YouTube’s Recommendation System for Ideologically Congenial, Extreme, and Problematic Recommendations,
  Proceedings of the National Academy of Sciences (PNAS) 2023 [PDF]
  M. Haroon, M. Wojcieszak, A. Chhabra, X. Liu, P. Mohapatra, Z. Shafiq
  
  

• An Overview of Fairness in Clustering,
  IEEE Access (2021) [PDF]
  A. Chhabra, K. Masalkovaite, P. Mohapatra
  
  

• Fair Clustering Using Antidote Data,
  AFCR @ NeurIPS (2021) [PDF]
  A. Chhabra, A. Singla, P. Mohapatra
  
  

• Tensorflex: Tensorflow Bindings for the Elixir Programming Language,
  MLOSS @ NeurIPS (2018) [PDF]
  A. Chhabra, J. Valim
  
  

• A Moving Target Defense Against Adversarial Machine Learning,
  ACM/IEEE Symposium on Edge Computing (2019) [PDF]
  A. Roy, A. Chhabra, C. Kamhoua, P. Mohapatra
  
  

• Fair Algorithms for Hierarchical Agglomerative Clustering,
  IEEE ICMLA (2022) [PDF]
  A. Chhabra, P. Mohapatra
  
  

• Understanding Flows in High-Speed Scientific Networks: A Netflow Data Study,
  Future Generation Computer Systems (2019) [PDF]
  M. Kiran, A. Chhabra
  
  

• GMMR: A Gaussian Mixture Model Based Unsupervised Machine Learning Approach for Optimal Routing in Opportunistic IoT Networks,
  Computer Communications (2019) [PDF]
  V. Vashishth, A. Chhabra, D.K. Sharma
  
  

• Enabling Security for the Industrial Internet of Things using Deep Learning, Blockchain, and Coalitions,
  Transactions on Emerging Telecommunications Technologies (2021) [PDF]
  M. Sharma, S. Pant, D.K. Sharma, K.D. Gupta, V. Vashishth, A. Chhabra
  
  

• RLProph: A Dynamic Programming Based Reinforcement Learning Approach for Optimal Routing in Opportunistic IoT Networks,
  Wireless Networks (2020) [PDF]
  D.K. Sharma, J.J.P.C. Rodrigues, V. Vashishth, A. Khanna, A. Chhabra