Search Results for author:
Found 34 papers, 9 papers with code
Mitigating Data Shift of Biomedical Research Articles for Information Retrieval and Semantic Indexing
Our results show that the model effectively leverages task similarity to improve the robustness to dataset shift.
COVID-19 Surveillance through Twitter using Self-Supervised and Few Shot Learning
Public health surveillance and tracking virus via social media can be a useful digital tool for contact tracing and preventing the spread of the virus.
Hate and Toxic Speech Detection in the Context of Covid-19 Pandemic using XAI: Ongoing Applied Research
As social distancing, self-quarantines, and travel restrictions have shifted a lot of pandemic conversations to social media so does the spread of hate speech.
Explainable Artificial Intelligence (XAI)
Feature Importance
+2
CAMOUFLAGE: Exploiting Misinformation Detection Systems Through LLM-driven Adversarial Claim Transformation
Existing black-box text-based adversarial attacks are ill-suited for evidence-based misinformation detection systems, as these attacks primarily focus on token-level substitutions involving gradient or logit-based optimization strategies, which are incapable of fooling the multi-component nature of these detection systems.
Machine Learning Fairness in House Price Prediction: A Case Study of America's Expanding Metropolises
As a result, it finds that the ML-driven house price prediction models show various levels of bias towards protected attributes (i. e., race and ethnicity in this study).
FLAVARS: A Multimodal Foundational Language and Vision Alignment Model for Remote Sensing
Remote sensing imagery is dense with objects and contextual visual information.
Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries
Subsequently, we fine-tune state-of-the-art LLMs using DeBinVul and report on a performance increase of 19%, 24%, and 21% in the capabilities of CodeLlama, Llama3, and CodeGen2 respectively, in detecting binary code vulnerabilities.
Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent
To leverage the strengths of both multi-agent reasoning and ToT strategies, we introduce a novel approach combining ToT-based Reasoner agents with a Thought Validator agent.
Jailbreaking Large Language Models with Symbolic Mathematics
Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation.
AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
Recent advancements in automatic code generation using large language models (LLMs) have brought us closer to fully automated secure software development.
Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs
With the recent unprecedented advancements in Artificial Intelligence (AI) computing, progress in Large Language Models (LLMs) is accelerating rapidly, presenting challenges in establishing clear guidelines, particularly in the field of security.
Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysis
To address these challenges, we conducted a comprehensive study evaluating the efficacy of existing methods in helping junior developers secure their code.
Enhancing Event Reasoning in Large Language Models through Instruction Fine-Tuning with Semantic Causal Graphs
Our evaluations demonstrate that training LLMs with SCG Instructions outperforms standard instruction fine-tuning by an average of 35. 69\% on Event Trigger Classification.
Estimating Earthquake Magnitude in Sentinel-1 Imagery via Ranking
Earthquakes are commonly estimated using physical seismic stations, however, due to the installation requirements and costs of these stations, global coverage quickly becomes impractical.
On the Consistency of Fairness Measurement Methods for Regression Tasks
With growing applications of Machine Learning (ML) techniques in the real world, it is highly important to ensure that these models work in an equitable manner.
Image Safeguarding: Reasoning with Conditional Vision Language Model and Obfuscating Unsafe Content Counterfactually
This process involves addressing two key problems: (1) the reason for obfuscating unsafe images demands the platform to provide an accurate rationale that must be grounded in unsafe image-specific attributes, and (2) the unsafe regions in the image must be minimally obfuscated while still depicting the safe regions.
Lateral Phishing With Large Language Models: A Large Organization Comparative Study
The emergence of Large Language Models (LLMs) has heightened the threat of phishing emails by enabling the generation of highly targeted, personalized, and automated attacks.
Deciphering Textual Authenticity: A Generalized Strategy through the Lens of Large Language Semantics for Detecting Human vs. Machine-Generated Text
We first study the effectiveness of state-of-the-art approaches and find that they are severely limited against text produced by diverse generators and domains in the real world.
Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models
This imbalance between the lines needed for security measures and the functional code enforces the supervised fine-tuned model to prioritize generating functional code without adding proper security measures, which also benefits the model by resulting in minimal loss.
Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery
In this work we propose a road segmentation benchmark dataset, Chesapeake Roads Spatial Context (RSC), for evaluating the spatial long-range context understanding of geospatial machine learning models and show how commonly used semantic segmentation models can fail at this task.
Ranked #1 on
Road Segmentation
on ChesapeakeRSC
LLM-Powered Code Vulnerability Repair with Reinforcement Learning and Semantic Reward
In software development, the predominant emphasis on functionality often supersedes security concerns, a trend gaining momentum with AI-driven automation tools like GitHub Copilot.
Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters
Research in self-supervised learning (SSL) with natural images has progressed rapidly in recent years and is now increasingly being applied to and benchmarked with datasets containing remotely sensed imagery.
Single-View Height Estimation with Conditional Diffusion Probabilistic Models
Digital Surface Models (DSM) offer a wealth of height information for understanding the Earth's surface as well as monitoring the existence or change in natural and man-made structures.
ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding
A crucial part of any home is the roof over our heads to protect us from the elements.
An Unbiased Transformer Source Code Learning with Semantic Vulnerability Graph
We present a training process utilizing a semantic vulnerability graph (SVG) representation from source code, created by integrating edges from a sequential flow, control flow, and data flow, as well as a novel flow dubbed Poacher Flow (PF).
Supervising Remote Sensing Change Detection Models with 3D Surface Semantics
Remote sensing change detection, identifying changes between scenes of the same location, is an active area of research with a broad range of applications.
Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts
To overcome this problem, we propose a Multimodal Variational Auto-Encoder (M-VAE) which can learn the shared latent space of image features and the semantic space.
Interpretable Self-supervised Multi-task Learning for COVID-19 Information Retrieval and Extraction
Our model outperforms baselines in IE and IR tasks, respectively by micro-f score of 0. 08 (LCA-F score of 0. 05), and MAP of 0. 05 on average.
Show Why the Answer is Correct! Towards Explainable AI using Compositional Temporal Attention
This results in achieving better understanding of complex questions and also provides reasoning as to why the module predicts a particular answer.
Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purification
In order to evaluate the most adequate SRD, we rely on the distance between robust latent representations and semantic cluster distributions.
A Self-supervised Approach for Semantic Indexing in the Context of COVID-19 Pandemic
We present a case study on a novel dataset that is based on COVID-19 papers published and manually indexed in PubMed.
Learning from Few Samples: A Survey
Deep neural networks have been able to outperform humans in some cases like image recognition and image classification.
Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey
We provide a taxonomy to classify adversarial attacks and defenses, formulate the Robust Optimization problem in a min-max setting and divide it into 3 subcategories, namely: Adversarial (re)Training, Regularization Approach, and Certified Defenses.
