Anshuman Chhabra

Anshuman Chhabra, Ashwin Sekhari, Prasant Mohapatra

Clustering models constitute a class of unsupervised machine learning methods which are used in a number of application pipelines, and play a vital role in modern data science. With recent advancements in deep learning -- deep clustering models have emerged as the current state-of-the-art over traditional clustering approaches, especially for high-dimensional image datasets. While traditional clustering approaches have been analyzed from a robustness perspective, no prior work has investigated adversarial attacks and robustness for deep clustering models in a principled manner. To bridge this gap, we propose a blackbox attack using Generative Adversarial Networks (GANs) where the adversary does not know which deep clustering model is being used, but can query it for outputs. We analyze our attack against multiple state-of-the-art deep clustering models and real-world datasets, and find that it is highly successful. We then employ some natural unsupervised defense approaches, but find that these are unable to mitigate our attack. Finally, we attack Face++, a production-level face clustering API service, and find that we can significantly reduce its performance as well. Through this work, we thus aim to motivate the need for truly robust deep clustering models.

Shahriar Kabir Nahin, Hadi Askari, Muhao Chen et al.

Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the best output. A tacit premise behind TTS is that sufficiently diverse candidate pools enhance reliability. In this work, we show that this assumption in TTS introduces a previously unrecognized failure mode. When candidate diversity is curtailed, even by a modest amount, TTS becomes much more likely to produce unsafe outputs. We present a reference-guided diversity reduction protocol (RefDiv) that serves as a diagnostic attack to stress test TTS pipelines. Through extensive experiments across four open-source models (Qwen3, Mistral, Llama3.1, Gemma3) and two widely used TTS strategies (Monte Carlo Tree Search and Best-of-N), constraining diversity consistently signifies the rate at which TTS produces unsafe results. The effect is often stronger than that produced by prompts directly with high adversarial intent scores. This observed phenomenon also transfers across TTS strategies and to closed-source models (e.g. OpenAI o3 and Gemini-2.5-Pro), thus indicating that this is a general and extant property of TTS rather than a model-specific artifact. Additionally, we find that numerous widely used safety guardrail classifiers (e.g. Llama-Guard and OpenAI Moderation API), are unable to flag the adversarial input prompts generated by RefDiv, demonstrating that existing defenses offer limited protection against this diversity-driven failure mode. Through this work, we hope to motivate future research on designing robust TTS strategies that are both effective and secure against diversity-targeted stress tests as illustrated by RefDiv.

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.

Hadi Askari, Anshuman Chhabra, Bernhard Clemm von Hohenberg et al.

Polarization, declining trust, and wavering support for democratic norms are pressing threats to U.S. democracy. Exposure to verified and quality news may lower individual susceptibility to these threats and make citizens more resilient to misinformation, populism, and hyperpartisan rhetoric. 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 large-scale two-week long field experiment (from 1/19/2023 to 2/3/2023) 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 two hardcoded elements: a URL to the topic-relevant section of quality news organization and an encouragement to follow its Twitter account. To further test differential effects by gender of the bots, treated users were randomly assigned to receive responses by bots presented as female or male. We examine whether our over-time intervention enhances the following of news media organization, the sharing and the liking of news content and the tweeting about politics and the liking of political content. We find that the treated users followed more news accounts and the users in the female bot treatment were more likely to like news content than the control. Most of these results, however, were small in magnitude and confined to the already politically interested Twitter users, as indicated by their pre-treatment tweeting about politics. These findings have implications for social media and news organizations, and also offer direction for future work on how Large Language Models and other computational interventions can effectively enhance individual on-platform engagement with quality news and public affairs.

Hadi Askari, Shivanshu Gupta, Fei Wang et al.

Pretrained Large Language Models (LLMs) achieve strong performance across a wide range of tasks, yet exhibit substantial variability in the various layers' training quality with respect to specific downstream applications, limiting their downstream performance. It is therefore critical to estimate layer-wise training quality in a manner that accounts for both model architecture and training data. However, existing approaches predominantly rely on model-centric heuristics (such as spectral statistics, outlier detection, or uniform allocation) while overlooking the influence of data. To address these limitations, we propose LayerIF, a data-driven framework that leverages Influence Functions to quantify the training quality of individual layers in a principled and task-sensitive manner. By isolating each layer's gradients and measuring the sensitivity of the validation loss to training examples by computing layer-wise influences, we derive data-driven estimates of layer importance. Notably, our method produces task-specific layer importance estimates for the same LLM, revealing how layers specialize for different test-time evaluation tasks. We demonstrate the utility of our scores by leveraging them for two downstream applications: (a) expert allocation in LoRA-MoE architectures and (b) layer-wise sparsity distribution for LLM pruning. Experiments across multiple LLM architectures demonstrate that our model-agnostic, influence-guided allocation leads to consistent gains in task performance.

Hadi Askari, Shivanshu Gupta, Terry Tong et al.

In this work, we introduce a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection strategies tailored for two distinct real-world scenarios: Mixture of Tasks and Noisy ICL. We systematically evaluate the effectiveness of Influence Functions (IFs) as a selection tool for these settings, highlighting the potential of IFs to better capture the informativeness of examples within the demonstration pool. For the Mixture of Tasks setting, demonstrations are drawn from 28 diverse tasks, including MMLU, BigBench, StrategyQA, and CommonsenseQA. We demonstrate that combining BertScore-Recall (BSR) with an IF surrogate model can further improve performance, leading to average absolute accuracy gains of 0.37\% and 1.45\% for 3-shot and 5-shot setups when compared to traditional ICL metrics. In the Noisy ICL setting, we examine scenarios where demonstrations might be mislabeled or have adversarial noise. Our experiments show that reweighting traditional ICL selectors (BSR and Cosine Similarity) with IF-based selectors boosts accuracy by an average of 2.90\% for Cosine Similarity and 2.94\% for BSR on noisy GLUE benchmarks. For the adversarial sub-setting, we show the utility of using IFs for task-agnostic demonstration selection for backdoor attack mitigation. Showing a 32.89\% reduction in Attack Success Rate compared to task-aware methods. In sum, we propose a robust framework for demonstration selection that generalizes beyond traditional ICL, offering valuable insights into the role of IFs for Indirect ICL.

Shrestha Datta, Hongfu Liu, Anshuman Chhabra

Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserving its behavior on all other inputs. This process typically involves two stages: identifying the layer to edit and performing the parameter update. Intuitively, different queries may localize knowledge at different depths of the model, resulting in different sample-wise editing performance for a fixed editing layer. In this work, we hypothesize the existence of fixed golden layers that can achieve near-optimal editing performance similar to sample-wise optimal layers. To validate this hypothesis, we provide empirical evidence by comparing golden layers against ground-truth sample-wise optimal layers. Furthermore, we show that golden layers can be reliably identified using a proxy dataset and generalize effectively to unseen test set queries across datasets. Finally, we propose a novel method, namely Layer Gradient Analysis (LGA) that estimates golden layers efficiently via gradient-attribution, avoiding extensive trial-and-error across multiple editing runs. Extensive experiments on several benchmark datasets demonstrate the effectiveness and robustness of our LGA approach across different LLM types and various knowledge editing methods.

Shahriar Kabir Nahin, Wenxiao Xiao, Joshua Liu et al.

Data-centric learning seeks to improve model performance from the perspective of data quality, and has been drawing increasing attention in the machine learning community. Among its key tools, influence functions provide a powerful framework to quantify the impact of individual training samples on model predictions, enabling practitioners to identify detrimental samples and retrain models on a cleaner dataset for improved performance. However, most existing work focuses on the question: "what data benefits the learning model?" In this paper, we take a step further and investigate a more fundamental question: "what is the performance ceiling of the learning model?" Unlike prior studies that primarily measure improvement through overall accuracy, we emphasize category-wise accuracy and aim for Pareto improvements, ensuring that every class benefits, rather than allowing tradeoffs where some classes improve at the expense of others. To address this challenge, we propose category-wise influence functions and introduce an influence vector that quantifies the impact of each training sample across all categories. Leveraging these influence vectors, we develop a principled criterion to determine whether a model can still be improved, and further design a linear programming-based sample reweighting framework to achieve Pareto performance improvements. Through extensive experiments on synthetic datasets, vision, and text benchmarks, we demonstrate the effectiveness of our approach in estimating and achieving a model's performance improvement across multiple categories of interest.

Mahammed Kamruzzaman, Abdullah Al Monsur, Gene Louis Kim et al.

Emotions are a fundamental facet of human experience, varying across individuals, cultural contexts, and nationalities. Given the recent success of Large Language Models (LLMs) as role-playing agents, we examine whether LLMs exhibit emotional stereotypes when assigned nationality-specific personas. Specifically, we investigate how different countries are represented in pre-trained LLMs through emotion attributions and whether these attributions align with cultural norms. To provide a deeper interpretive lens, we incorporate four key cultural dimensions, namely Power Distance, Uncertainty Avoidance, Long-Term Orientation, and Individualism, derived from Hofstedes cross-cultural framework. Our analysis reveals significant nationality-based differences, with emotions such as shame, fear, and joy being disproportionately assigned across regions. Furthermore, we observe notable misalignment between LLM-generated and human emotional responses, particularly for negative emotions, highlighting the presence of reductive and potentially biased stereotypes in LLM outputs.

Hadi Askari, Anshuman Chhabra, Muhao Chen et al.

Large Language Models (LLMs) have achieved state-of-the-art performance at zero-shot generation of abstractive summaries for given articles. However, little is known about the robustness of such a process of zero-shot summarization. To bridge this gap, we propose relevance paraphrasing, a simple strategy that can be used to measure the robustness of LLMs as summarizers. The relevance paraphrasing approach identifies the most relevant sentences that contribute to generating an ideal summary, and then paraphrases these inputs to obtain a minimally perturbed dataset. Then, by evaluating model performance for summarization on both the original and perturbed datasets, we can assess the LLM's one aspect of robustness. We conduct extensive experiments with relevance paraphrasing on 4 diverse datasets, as well as 4 LLMs of different sizes (GPT-3.5-Turbo, Llama-2-13B, Mistral-7B, and Dolly-v2-7B). Our results indicate that LLMs are not consistent summarizers for the minimally perturbed articles, necessitating further improvements.

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.

Anshuman Chhabra, Abhishek Roy, Prasant Mohapatra

Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science, recent research has also started focusing on the security properties of these models. There has been a lot of work undertaken to understand if (deep) neural network architectures are resilient to black-box adversarial attacks which craft perturbed input samples that fool the classifier without knowing the architecture used. Recent work has also focused on the transferability of adversarial attacks and found that adversarial attacks are generally easily transferable between models, datasets, and techniques. However, such attacks and their analysis have not been covered from the perspective of unsupervised machine learning algorithms. In this paper, we seek to bridge this gap through multiple contributions. We first provide a strong (iterative) black-box adversarial attack that can craft adversarial samples which will be incorrectly clustered irrespective of the choice of clustering algorithm. We choose 4 prominent clustering algorithms, and a real-world dataset to show the working of the proposed adversarial algorithm. Using these clustering algorithms we also carry out a simple study of cross-technique adversarial attack transferability.

Satvik Jain, Arun Balaji Buduru, Anshuman Chhabra

Cloud infrastructures are being increasingly utilized in critical infrastructures such as banking/finance, transportation and utility management. Sophistication and resources used in recent security breaches including those on critical infrastructures show that attackers are no longer limited by monetary/computational constraints. In fact, they may be aided by entities with large financial and human resources. Hence there is urgent need to develop predictive approaches for cyber defense to strengthen cloud infrastructures specifically utilized by critical infrastructures. Extensive research has been done in the past on applying techniques such as Game Theory, Machine Learning and Bayesian Networks among others for the predictive defense of critical infrastructures. However a major drawback of these approaches is that they do not incorporate probabilistic human behavior which limits their predictive ability. In this paper, a stochastic approach is proposed to predict less secure states in critical cloud systems which might lead to potential security breaches. These less-secure states are deemed as `risky' states in our approach. Markov Decision Process (MDP) is used to accurately incorporate user behavior(s) as well as operational behavior of the cloud infrastructure through a set of features. The developed reward/cost mechanism is then used to select appropriate `actions' to identify risky states at future time steps by learning an optimal policy. Experimental results show that the proposed framework performs well in identifying future `risky' states. Through this work we demonstrate the effectiveness of using probabilistic modeling (MDP) to predictively secure critical cloud infrastructures.