UIHash: Detecting Similar Android UIs through Grid-Based Visual Appearance Representation
Explore a novel grid-based approach for detecting similar Android user interfaces, focusing on security measures against UI spoofing and phishing through advanced visual appearance analysis.
INSIGHT: Attacking Industry-Adopted Learning Resilient Logic Locking Techniques Using Explainable Graph Neural Network
Discover how INSIGHT, an explainable Graph Neural Network attack method, breaks through learning resilient logic locking techniques used in hardware security and IP protection.
DARKFLEECE: Probing the Dark Side of Android Subscription Apps
Discover how DARKFLEECE detects malicious subscription apps on Android through dark pattern analysis, featuring a 93.43% accurate automated detection system and insights for developers, users, and regulators.
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
Explore how DP-SGD provides stronger privacy guarantees for similar datapoints in deep learning, revealing why common benchmarks leak less information than previously estimated.
Can I Hear Your Face? Pervasive Attack on Voice Authentication Systems with a Single Face Image
Explore how Foice deepfake technology generates synthetic voices from single facial images to breach voice authentication systems, demonstrating vulnerabilities in major security platforms.
Instruction Backdoor Attacks Against Customized Large Language Models
Explore groundbreaking research on instruction backdoor attacks targeting customized LLMs, examining vulnerabilities in GPT applications and proposing effective defense strategies against security threats.
Differentially Private Diffusion Probabilistic Models for Image Synthesis
Explore how dp-promise leverages diffusion model noise to achieve differential privacy in image synthesis while maintaining high image quality and protecting sensitive training data.
PhishDecloaker: Detecting CAPTCHA-cloaked Phishing Websites via Hybrid Vision-based Interactive Models
Discover how PhishDecloaker uses AI and computer vision to detect CAPTCHA-protected phishing websites, improving detection rates from 0% to 74.25% and enhancing cybersecurity defenses.
Measuring Structural Limitations of Deepfake Media Datasets - A Systematic Review
Explore structural limitations in deepfake media datasets, examining metrics, generation techniques, and class distributions to understand their impact on detection systems and research reproducibility.
Neural Network Extraction Through Physical Side Channels - A Systematic Review
Explore physical side-channel analysis attacks on deep neural networks, examining threat models, attack methodologies, and practical limitations for model extraction and input recovery on hardware accelerators.
Exploiting Online Games - Security Issues in MMORPGs and Virtual Economies
Delve into online gaming security vulnerabilities, cheating mechanisms, and protective measures with insights from gaming security expert Gary McGraw, exploring privacy concerns and bot creation in MMORPGs.
Building a Conversational PDF Bot with LlamaIndex, Nvidia NIM, and Streamlit
Master building a conversational PDF bot using Streamlit, LlamaIndex, and Nvidia NIM to create interactive document-based chat applications with advanced RAG capabilities.
Python and Generative AI Projects for Beginners - Building Applications and Machine Learning Systems
Master Python programming while building practical GenAI projects, from basic word games to advanced applications like face recognition, chatbots, and recommendation systems. Includes hands-on data analysis and visualization.
Can LLMs Keep a Secret? - Privacy and Security in Large Language Models
Explore the critical aspects of privacy and security in Large Language Models through an in-depth analysis of their ability to protect sensitive information.
Anticipation and Collective Surprise in Information Theory and Consciousness
Explore the intersection of consciousness theories, information processing, and surprise mechanisms in the brain, examining integrated approaches to understanding predictive cognition and sensory anticipation.
NotebookLM Tutorial: Six Essential Use Cases for Research and Learning
Discover six innovative ways to leverage NotebookLM for research, study guides, personal coaching, health management, and career development while learning how to effectively organize and analyze information.
Navigating Autonomy - Security Experts' Perspectives on Augmented Intelligence in Cybersecurity
Explore security experts' insights on AI integration in cybersecurity, examining trust factors, autonomy levels, and human-AI collaboration frameworks for optimal threat response.
The Power of Words: Generating PowerShell Attacks from Natural Language
Explore how AI and Neural Machine Translation can automatically generate offensive PowerShell code from natural language, with insights into dataset creation and model performance evaluation.
Extracting Structured Data from Multi-Modal Input: Neural and Neuro-Symbolic Approaches
Explore advanced techniques for extracting structured data from multi-modal sources, focusing on neural methods, neuro-symbolic approaches, and LLM-based solutions for processing integrated text and visual elements.
Sequential Decision Making Under Uncertainty - Information Asymmetry in AI Systems
Delve into sequential decision-making under uncertainty, exploring persuasion and mechanism design in information asymmetry scenarios, with applications to AI and dynamic modeling frameworks.
Cognitive Mechanisms That Power Learning and Creativity
Explore the fascinating intersection of neuroscience and creativity, examining how working memory drives learning and innovative thinking, with insights for developing more effective AI systems.