Academic papers, new techniques, benchmarks, and theoretical findings in AI/LLM security.
This survey article examines how generative AI (machine learning models that create new content) can produce deepfakes (synthetic media where a person's face or voice is digitally manipulated to appear authentic) and discusses methods for detecting them. The paper reviews the current state of deepfake creation and detection technologies, providing an outlook on future developments in this rapidly evolving field.
This academic survey examines how AI and intelligent technologies affect security in IoV (Internet of Vehicles, where cars and vehicles connect to networks and each other). The paper discusses integrating edge computing (processing data on devices near the source rather than sending everything to distant servers) with AI to improve IoV security, exploring both benefits and challenges in this emerging field.
This is a research survey article that compares security risks across different types of AI systems, including LLMs (large language models, which are AI systems trained on massive amounts of text), AI agents (programs that can make decisions and take actions autonomously), and embodied agents (AI systems that interact with the physical world through robots or similar hardware). The article examines various security threats that affect these different AI systems and how those risks differ between them.
This academic paper describes HPGA, an algorithm designed to anonymize graph data (networks of connected nodes and edges) while preserving personalized information. The research, published in December 2026, addresses the challenge of protecting privacy in graph-structured datasets, which are commonly used in social networks and recommendation systems.
This academic paper presents a new method for detecting intrusions (unauthorized access or attacks) in Industrial Control Systems (ICS, which are computers that manage physical infrastructure like power plants or factories) by combining temporal data (information about when events happen) with symbolic data (categorical information like event types). The approach aims to improve security monitoring in critical infrastructure by better identifying suspicious network activity patterns.
OWASP, a major open-source security organization, has released a 2026 Top 10 list of security risks specific to LLM (large language model) applications and introduced a new standard for controlling AI agents (autonomous programs that can perform tasks independently). The project, which now has over 30,000 members, aims to help developers and organizations understand and address the most critical security threats in generative AI systems.
ATLAS v2026.08 is an updated knowledge base documenting adversary tactics and techniques involving AI systems, including attacks against AI-enabled systems and abuse of AI capabilities, based on real-world observations and security research. The update adds new techniques related to autonomous AI agents (such as reconnaissance, attack coordination, and communication between agents), new mitigations for controlling AI agent behavior, and case studies of actual AI-related attacks on infrastructure and government systems.
This academic paper examines security attacks targeting industrial control systems (ICS, which are computers that manage factories, power plants, and other critical infrastructure) when they communicate over wireless networks. The research, published in December 2026, explores vulnerabilities in these wireless connections that attackers could exploit to disrupt or damage essential infrastructure.
This is a systematic review article that examines security and privacy-preserving mechanisms used in collaborative machine learning (where multiple organizations or parties train AI models together while protecting their sensitive data). The article organizes existing approaches into a novel taxonomy, helping researchers and practitioners understand different methods for keeping data secure during collaborative AI training.
A study of over 1,000 first-year students at Bocconi University found that access to ChatGPT (a large language model, or LLM) improved the quality and professionalism of student work on a business assignment, while separate training in causal reasoning (a form of critical thinking involving understanding cause-and-effect relationships) led students to generate more original and diverse ideas. Students who received both ChatGPT access and critical-thinking training showed benefits from each approach, suggesting that AI tools and thinking skills are complementary rather than competing.
This survey article examines how generative AI (machine learning models that can create new content) is being used to produce deepfakes (synthetic media where a person's face or voice is digitally manipulated to appear authentic) and discusses methods to detect them. The paper reviews current techniques for both creating and identifying deepfakes, and considers future challenges in an era where AI-generated content is becoming increasingly sophisticated and difficult to distinguish from real media.
This academic survey examines how AI and intelligent technologies affect security in IoV (Internet of Vehicles, where connected cars communicate with each other and infrastructure). The paper discusses integrating edge computing (processing data closer to vehicles rather than in distant data centers) with AI to improve IoV security, though specific vulnerabilities and their fixes are not detailed in this overview.
This is a research survey paper published in ACM Computing Surveys that compares security risks across different types of AI systems, including LLMs (large language models, which are AI systems trained on massive amounts of text), AI agents (systems that can take actions based on their decisions), and embodied agents (AI systems that interact with the physical world through robots or similar devices). The paper examines and contrasts the various security vulnerabilities and threats that each of these AI system types faces.
Researchers have developed a method for encrypting images using deep learning combined with chaotic systems (mathematical systems that produce unpredictable, random-looking outputs). The approach reconstructs chaotic patterns using neural networks to create a security system that scrambles images in a way that makes them unreadable without the correct decryption key.
FlexDPI is a system for deep packet inspection (DPI, where network traffic is examined in detail to monitor what data is being sent) that aims to protect user privacy while still allowing network monitoring. The research presents a method that lets users choose which security rules apply to their traffic, while using verification techniques to ensure the system works correctly without exposing sensitive information.
This academic paper proposes a new authentication system that combines blockchain (a distributed ledger technology that records data across many computers) with privacy protection methods for military surveillance applications in 6G (the next generation of wireless networks). The framework is designed to allow secure identification and verification of users while keeping their personal information hidden from unauthorized access.
BEdX25519 is a lightweight authenticated key exchange protocol (a method for two devices to securely agree on encryption keys) designed for IoT (Internet of Things) devices to communicate directly with each other using blockchain (a distributed ledger technology) and elliptic curve cryptography (a type of mathematical encryption based on curves). The protocol aims to make secure device-to-device communication more efficient for resource-constrained IoT systems.
This academic paper, published in September 2026, describes a method for securely accessing encrypted data using hardware tokens (physical devices that store security credentials). The research presents a scheme designed to protect data while allowing authorized users to access it through these specialized hardware devices.
This academic paper describes a method for protecting videos using watermarking (a technique that embeds hidden information into media to prove ownership or detect tampering) by applying multiple mathematical transformations to make the watermark resistant to attacks. The research, published in November 2026, proposes using orthogonal transformations (mathematical operations that preserve certain properties) in combination to create a hybrid approach that is harder for attackers to remove or corrupt.
This academic paper proposes an improved authentication scheme for IoV (Internet of Vehicles, where connected cars communicate with each other and infrastructure) based on an enhanced BLS signature algorithm (a cryptographic method for verifying that a message came from a legitimate source). The research focuses on making vehicle authentication more efficient while maintaining security for connected vehicle systems.