arXiv subjects

Ayush Kumar

Publications and source records attributed to Ayush Kumar.

At least 37 records · Page 2Linked to original sources

arXiv2023

Towards Probing Contact Center Large Language Models

Fine-tuning large language models (LLMs) with domain-specific instructions has emerged as an effective method to enhance their domain-specific understanding. Yet, there is limited work that examines the core characteristics acquired during this process. In this study, we benchmark the fundamental characteristics learned by contact-center (CC) specific instruction fine-tuned LLMs with out-of-the-box (OOB) LLMs via probing tasks encompassing conversational, channel, and automatic speech recognition (ASR) properties. We explore different LLM architectures (Flan-T5 and Llama), sizes (3B, 7B, 11B, 13B), and fine-tuning paradigms (full fine-tuning vs PEFT). Our findings reveal remarkable effectiveness of CC-LLMs on the in-domain downstream tasks, with improvement in response acceptability by over 48% compared to OOB-LLMs. Additionally, we compare the performance of OOB-LLMs and CC-LLMs on the widely used SentEval dataset, and assess their capabilities in terms of surface, syntactic, and semantic information through probing tasks. Intriguingly, we note a relatively consistent performance of probing classifiers on the set of probing tasks. Our observations indicate that CC-LLMs, while outperforming their out-of-the-box counterparts, exhibit a tendency to rely less on encoding surface, syntactic, and semantic properties, highlighting the intricate interplay between domain-specific adaptation and probing task performance opening up opportunities to explore behavior of fine-tuned language models in specialized contexts.

cs.CL↗

arXiv2023

Malicious Lateral Movement in 5G Core With Network Slicing And Its Detection

5G networks are susceptible to cyber attacks due to reasons such as implementation issues and vulnerabilities in 3GPP standard specifications. In this work, we propose lateral movement strategies in a 5G Core (5GC) with network slicing enabled, as part of a larger attack campaign by well-resourced adversaries such as APT groups. Further, we present 5GLatte, a system to detect such malicious lateral movement. 5GLatte operates on a host-container access graph built using host/NF container logs collected from the 5GC. Paths inferred from the access graph are scored based on selected filtering criteria and subsequently presented as input to a threshold-based anomaly detection algorithm to reveal malicious lateral movement paths. We evaluate 5GLatte on a dataset containing attack campaigns (based on MITRE ATT&CK and FiGHT frameworks) launched in a 5G test environment which shows that compared to other lateral movement detectors based on state-of-the-art, it can achieve higher true positive rates with similar false positive rates.

cs.CR↗

arXiv2023

RAPTOR: Advanced Persistent Threat Detection in Industrial IoT via Attack Stage Correlation

Past Advanced Persistent Threat (APT) attacks on Industrial Internet-of-Things (IIoT), such as the 2016 Ukrainian power grid attack and the 2017 Saudi petrochemical plant attack, have shown the disruptive effects of APT campaigns while new IIoT malware continue to be developed by APT groups. Existing APT detection systems have been designed using cyberattack TTPs modelled for enterprise IT networks and leverage specific data sources (e.g., Linux audit logs, Windows event logs) which are not found on ICS devices. In this work, we propose RAPTOR, a system to detect APT campaigns in IIoT. Using cyberattack TTPs modelled for ICS/OT environments and focusing on "invariant" attack phases, RAPTOR detects and correlates various APT attack stages in IIoT leveraging data which can be readily collected from ICS devices/networks (packet traffic traces, IDS alerts). Subsequently, it constructs a high-level APT campaign graph which can be used by cybersecurity analysts towards attack analysis and mitigation. A performance evaluation of RAPTOR's APT attack-stage detection modules shows high precision and low false positive/negative rates. We also show that RAPTOR is able to construct the APT campaign graph for APT attacks (modelled after real-world attacks on ICS/OT infrastructure) executed on our IIoT testbed.

cs.CR↗

arXiv2023

A Public Key Infrastructure for 5G Service-Based Architecture

The 3GPP 5G Service-based Architecture (SBA) security specifications leave several details on how to setup an appropriate Public Key Infrastructure (PKI) for 5G SBA, unspecified. In this work, we propose 5G-SBA-PKI, a public key infrastructure for secure inter-NF communication in 5G SBA core networks, where NF refers to Network Functions. 5G-SBA-PKI is designed to include multiple certificate authorities (with different scopes of operation and capabilities) at different PLMN levels for certification operations and key exchange between communicating NFs, where PLMN refers to a Public Land Mobile Network. We conduct a formal analysis of 5G-SBA-PKI with respect to the desired security properties using TAMARIN prover. Finally, we evaluate 5G-SBA-PKI's performance with "pre-quantum" as well as quantum-safe cryptographic algorithms.

cs.CR↗

arXiv2023

A Testbed To Study Adversarial Cyber-Attack Strategies in Enterprise Networks

In this work, we propose a testbed environment to capture the attack strategies of an adversary carrying out a cyber-attack on an enterprise network. The testbed contains nodes with known security vulnerabilities which can be exploited by hackers. Participants can be invited to play the role of a hacker (e.g., black-hat, hacktivist) and attack the testbed. The testbed is designed such that there are multiple attack pathways available to hackers. We describe the working of the testbed components and discuss its implementation on a VMware ESXi server. Finally, we subject our testbed implementation to a few well-known cyber-attack strategies, collect data during the process and present our analysis of the data.

cs.CR↗

arXiv2023

Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization

LLM-powered chatbots are becoming widely adopted in applications such as healthcare, personal assistants, industry hiring decisions, etc. In many of these cases, chatbots are fed sensitive, personal information in their prompts, as samples for in-context learning, retrieved records from a database, or as part of the conversation. The information provided in the prompt could directly appear in the output, which might have privacy ramifications if there is sensitive information there. As such, in this paper, we aim to understand the input copying and regurgitation capabilities of these models during inference and how they can be directly instructed to limit this copying by complying with regulations such as HIPAA and GDPR, based on their internal knowledge of them. More specifically, we find that when ChatGPT is prompted to summarize cover letters of a 100 candidates, it would retain personally identifiable information (PII) verbatim in 57.4% of cases, and we find this retention to be non-uniform between different subgroups of people, based on attributes such as gender identity. We then probe ChatGPT's perception of privacy-related policies and privatization mechanisms by directly instructing it to provide compliant outputs and observe a significant omission of PII from output.

cs.CL↗

arXiv2022

Deep Learning Driven Natural Languages Text to SQL Query Conversion: A Survey

With the future striving toward data-centric decision-making, seamless access to databases is of utmost importance. There is extensive research on creating an efficient text-to-sql (TEXT2SQL) model to access data from the database. Using a Natural language is one of the best interfaces that can bridge the gap between the data and results by accessing the database efficiently, especially for non-technical users. It will open the doors and create tremendous interest among users who are well versed in technical skills or not very skilled in query languages. Even if numerous deep learning-based algorithms are proposed or studied, there still is very challenging to have a generic model to solve the data query issues using natural language in a real-work scenario. The reason is the use of different datasets in different studies, which comes with its limitations and assumptions. At the same time, we do lack a thorough understanding of these proposed models and their limitations with the specific dataset it is trained on. In this paper, we try to present a holistic overview of 24 recent neural network models studied in the last couple of years, including their architectures involving convolutional neural networks, recurrent neural networks, pointer networks, reinforcement learning, generative models, etc. We also give an overview of the 11 datasets that are widely used to train the models for TEXT2SQL technologies. We also discuss the future application possibilities of TEXT2SQL technologies for seamless data queries.

cs.CL↗

arXiv2022

An Open Source Interactive Visual Analytics Tool for Comparative Programming Comprehension

This paper proposes an open source visual analytics tool consisting of several views and perspectives on eye movement data collected during code reading tasks when writing computer programs. Hence the focus of this work is on code and program comprehension. The source code is shown as a visual stimulus. It can be inspected in combination with overlaid scanpaths in which the saccades can be visually encoded in several forms, including straight, curved, and orthogonal lines, modifiable by interaction techniques. The tool supports interaction techniques like filter functions, aggregations, data sampling, and many more. We illustrate the usefulness of our tool by applying it to the eye movements of 216 programmers of multiple expertise levels that were collected during two code comprehension tasks. Our tool helped to analyze the difference between the strategic program comprehension of programmers based on their demographic background, time taken to complete the task, choice of programming task, and expertise.

cs.HC↗

arXiv2022

Eye Gaze Estimation Model Analysis

We explore techniques for eye gaze estimation using machine learning. Eye gaze estimation is a common problem for various behavior analysis and human-computer interfaces. The purpose of this work is to discuss various model types for eye gaze estimation and present the results from predicting gaze direction using eye landmarks in unconstrained settings. In unconstrained real-world settings, feature-based and model-based methods are outperformed by recent appearance-based methods due to factors like illumination changes and other visual artifacts. We discuss a learning-based method for eye region landmark localization trained exclusively on synthetic data. We discuss how to use detected landmarks as input to iterative model-fitting and lightweight learning-based gaze estimation methods and how to use the model for person-independent and personalized gaze estimations.

cs.CV↗

arXiv2022

Low Resource Pipeline for Spoken Language Understanding via Weak Supervision

In Weak Supervised Learning (WSL), a model is trained over noisy labels obtained from semantic rules and task-specific pre-trained models. Rules offer limited generalization over tasks and require significant manual efforts while pre-trained models are available only for limited tasks. In this work, we propose to utilize prompt-based methods as weak sources to obtain the noisy labels on unannotated data. We show that task-agnostic prompts are generalizable and can be used to obtain noisy labels for different Spoken Language Understanding (SLU) tasks such as sentiment classification, disfluency detection and emotion classification. These prompts could additionally be updated to add task-specific contexts, thus providing flexibility to design task-specific prompts. We demonstrate that prompt-based methods generate reliable labels for the above SLU tasks and thus can be used as a universal weak source to train a weak-supervised model (WSM) in absence of labeled data. Our proposed WSL pipeline trained over prompt-based weak source outperforms other competitive low-resource benchmarks on zero and few-shot learning by more than 4% on Macro-F1 on all of the three benchmark SLU datasets. The proposed method also outperforms a conventional rule based WSL pipeline by more than 5% on Macro-F1.

cs.CL↗

arXiv2022

Document Structure aware Relational Graph Convolutional Networks for Ontology Population

Ontologies comprising of concepts, their attributes, and relationships are used in many knowledge based AI systems. While there have been efforts towards populating domain specific ontologies, we examine the role of document structure in learning ontological relationships between concepts in any document corpus. Inspired by ideas from hypernym discovery and explainability, our method performs about 15 points more accurate than a stand-alone R-GCN model for this task.

cs.AI↗

arXiv2021

What BERT Based Language Models Learn in Spoken Transcripts: An Empirical Study

Language Models (LMs) have been ubiquitously leveraged in various tasks including spoken language understanding (SLU). Spoken language requires careful understanding of speaker interactions, dialog states and speech induced multimodal behaviors to generate a meaningful representation of the conversation. In this work, we propose to dissect SLU into three representative properties:conversational (disfluency, pause, overtalk), channel (speaker-type, turn-tasks) and ASR (insertion, deletion,substitution). We probe BERT based language models (BERT, RoBERTa) trained on spoken transcripts to investigate its ability to understand multifarious properties in absence of any speech cues. Empirical results indicate that LM is surprisingly good at capturing conversational properties such as pause prediction and overtalk detection from lexical tokens. On the downsides, the LM scores low on turn-tasks and ASR errors predictions. Additionally, pre-training the LM on spoken transcripts restrain its linguistic understanding. Finally, we establish the efficacy and transferability of the mentioned properties on two benchmark datasets: Switchboard Dialog Act and Disfluency datasets.

cs.CL↗

arXiv2021

Investigating Bias In Automatic Toxic Comment Detection: An Empirical Study

With surge in online platforms, there has been an upsurge in the user engagement on these platforms via comments and reactions. A large portion of such textual comments are abusive, rude and offensive to the audience. With machine learning systems in-place to check such comments coming onto platform, biases present in the training data gets passed onto the classifier leading to discrimination against a set of classes, religion and gender. In this work, we evaluate different classifiers and feature to estimate the bias in these classifiers along with their performance on downstream task of toxicity classification. Results show that improvement in performance of automatic toxic comment detection models is positively correlated to mitigating biases in these models. In our work, LSTM with attention mechanism proved to be a better modelling strategy than a CNN model. Further analysis shows that fasttext embeddings is marginally preferable than glove embeddings on training models for toxicity comment detection. Deeper analysis reveals the findings that such automatic models are particularly biased to specific identity groups even though the model has a high AUC score. Finally, in effort to mitigate bias in toxicity detection models, a multi-task setup trained with auxiliary task of toxicity sub-types proved to be useful leading to upto 0.26% (6% relative) gain in AUC scores.

cs.CL↗

arXiv2021

Chitrakar: Robotic System for Drawing Jordan Curve of Facial Portrait

This paper presents a robotic system (\textit{Chitrakar}) which autonomously converts any image of a human face to a recognizable non-self-intersecting loop (Jordan Curve) and draws it on any planar surface. The image is processed using Mask R-CNN for instance segmentation, Laplacian of Gaussian (LoG) for feature enhancement and intensity-based probabilistic stippling for the image to points conversion. These points are treated as a destination for a travelling salesman and are connected with an optimal path which is calculated heuristically by minimizing the total distance to be travelled. This path is converted to a Jordan Curve in feasible time by removing intersections using a combination of image processing, 2-opt, and Bresenham's Algorithm. The robotic system generates $n$ instances of each image for human aesthetic judgement, out of which the most appealing instance is selected for the final drawing. The drawing is executed carefully by the robot's arm using trapezoidal velocity profiles for jerk-free and fast motion. The drawing, with a decent resolution, can be completed in less than 30 minutes which is impossible to do by hand. This work demonstrates the use of robotics to augment humans in executing difficult craft-work instead of replacing them altogether.

cs.RO↗

arXiv2021

Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript

Recent years have witnessed significant improvement in ASR systems to recognize spoken utterances. However, it is still a challenging task for noisy and out-of-domain data, where substitution and deletion errors are prevalent in the transcribed text. These errors significantly degrade the performance of downstream tasks. In this work, we propose a BERT-style language model, referred to as PhonemeBERT, that learns a joint language model with phoneme sequence and ASR transcript to learn phonetic-aware representations that are robust to ASR errors. We show that PhonemeBERT can be used on downstream tasks using phoneme sequences as additional features, and also in low-resource setup where we only have ASR-transcripts for the downstream tasks with no phoneme information available. We evaluate our approach extensively by generating noisy data for three benchmark datasets - Stanford Sentiment Treebank, TREC and ATIS for sentiment, question and intent classification tasks respectively. The results of the proposed approach beats the state-of-the-art baselines comprehensively on each dataset.

eess.AS↗

arXiv2020

Machine Learning-Based Early Detection of IoT Botnets Using Network-Edge Traffic

In this work, we present a lightweight IoT botnet detection solution, EDIMA, which is designed to be deployed at the edge gateway installed in home networks and targets early detection of botnets prior to the launch of an attack. EDIMA includes a novel two-stage Machine Learning (ML)-based detector developed specifically for IoT bot detection at the edge gateway. The ML-based bot detector first employs ML algorithms for aggregate traffic classification and subsequently Autocorrelation Function (ACF)-based tests to detect individual bots. The EDIMA architecture also comprises a malware traffic database, a policy engine, a feature extractor and a traffic parser. Performance evaluation results show that EDIMA achieves high bot scanning and bot-CnC traffic detection accuracies with very low false positive rates. The detection performance is also shown to be robust to an increase in the number of IoT devices connected to the edge gateway where EDIMA is deployed. Further, the runtime performance analysis of a Python implementation of EDIMA deployed on a Raspberry Pi reveals low bot detection delays and low RAM consumption. EDIMA is also shown to outperform existing detection techniques for bot scanning traffic and bot-CnC server communication.

cs.CR↗

arXiv2020

BAKSA at SemEval-2020 Task 9: Bolstering CNN with Self-Attention for Sentiment Analysis of Code Mixed Text

Sentiment Analysis of code-mixed text has diversified applications in opinion mining ranging from tagging user reviews to identifying social or political sentiments of a sub-population. In this paper, we present an ensemble architecture of convolutional neural net (CNN) and self-attention based LSTM for sentiment analysis of code-mixed tweets. While the CNN component helps in the classification of positive and negative tweets, the self-attention based LSTM, helps in the classification of neutral tweets, because of its ability to identify correct sentiment among multiple sentiment bearing units. We achieved F1 scores of 0.707 (ranked 5th) and 0.725 (ranked 13th) on Hindi-English (Hinglish) and Spanish-English (Spanglish) datasets, respectively. The submissions for Hinglish and Spanglish tasks were made under the usernames ayushk and harsh_6 respectively.

cs.CL↗

arXiv2020

Gated Mechanism for Attention Based Multimodal Sentiment Analysis

Multimodal sentiment analysis has recently gained popularity because of its relevance to social media posts, customer service calls and video blogs. In this paper, we address three aspects of multimodal sentiment analysis; 1. Cross modal interaction learning, i.e. how multiple modalities contribute to the sentiment, 2. Learning long-term dependencies in multimodal interactions and 3. Fusion of unimodal and cross modal cues. Out of these three, we find that learning cross modal interactions is beneficial for this problem. We perform experiments on two benchmark datasets, CMU Multimodal Opinion level Sentiment Intensity (CMU-MOSI) and CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) corpus. Our approach on both these tasks yields accuracies of 83.9% and 81.1% respectively, which is 1.6% and 1.34% absolute improvement over current state-of-the-art.

cs.CL↗