336 matches found
Cybersecurity of High-Altitude Platform Stations: Threat Taxonomy, Attacks and Defenses with Standards Mapping - DDoS Attack Use Case
High-Altitude Platform Stations HAPS are emerging stratospheric nodes within non-terrestrial networks. We provide a structured overview of HAPS subsystems and principal communication links, map cybersecurity and privacy exposure across communication, control, and power subsystems, and propose a...
SoK: Systematizing a Decade of Architectural RowHammer Defenses through the Lens of Streaming Algorithms
A decade after its academic introduction, RowHammer RH remains a moving target that continues to challenge both the industry and academia. With its potential to serve as a critical attack vector, the ever-decreasing RH threshold now threatens DRAM process technology scaling, with a superlinearly...
Online Fraud and Abuse 2025: AI Is in the Driver’s Seat
...
AAGATE: A NIST AI RMF-Aligned Governance Platform for Agentic AI
This paper introduces the Agentic AI Governance Assurance & Trust Engine AAGATE, a Kubernetes-native control plane designed to address the unique security and governance challenges posed by autonomous, language-model-driven agents in production. Recognizing the limitations of traditional...
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
Agentic AI systems powered by large language models LLMs and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web, software, and physical environments creates new and amplified...
Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
With the wide application of deep reinforcement learning DRL techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable environments has become a core issue in current research...
Antivirus Software Outage: Is Your Defense Ready?
Your antivirus software is the trusted gatekeeper of your digital world, silently working in the background to block threats. But what happens when that gatekeeper suddenly walks off the job? A widespread antivirus software outage recently showed us the answer, grinding critical industries to a...
HAMLOCK: HArdware-Model LOgically Combined AttacK
The growing use of third-party hardware accelerators e.g., FPGAs, ASICs for deep neural networks DNNs introduces new security vulnerabilities. Conventional model-level backdoor attacks, which only poison a model's weights to misclassify inputs with a specific trigger, are often detectable because...
Toward Understanding Security Issues in the Model Context Protocol Ecosystem
The Model Context Protocol MCP is an emerging open standard that enables AI-powered applications to interact with external tools through structured metadata. A rapidly growing ecosystem has formed around MCP, including a wide range of MCP hosts i.e., Cursor, Windsurf, Claude Desktop, and Cline, M...
SoK: Taxonomy and Evaluation of Prompt Security in Large Language Models
Large Language Models LLMs have rapidly become integral to real-world applications, powering services across diverse sectors. However, their widespread deployment has exposed critical security risks, particularly through jailbreak prompts that can bypass model alignment and induce harmful outputs...
Extortion and ransomware drive over half of cyberattacks
In 80% of the cyber incidents Microsoft’s security teams investigated last year, attackers sought to steal data—a trend driven more by financial gain than intelligence gathering. According to the latest Microsoft Digital Defense Report, written with our Chief Information Security Officer Igor...
When the Call Comes from Inside: The Rising Threat of Insider Recruitment in Ransomware Campaigns
In cybersecurity, we often say that attackers only need to be right once – and defenders need to be right every time. Traditionally, we’ve focused on perimeter breaches, phishing campaigns, and zero-day exploits. But increasingly, attackers are bypassing these hardened defenses and taking a...
Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders and Researchers
Analyzing 500 CTF participants, this paper shows that while participants readily bypassed simple AI guardrails using common techniques, layered multi-step defenses still posed significant challenges, offering concrete insights for building safer AI systems...
Exploiting Web Search Tools of AI Agents for Data Exfiltration
Large language models LLMs are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation RAG allows LLMs to process and retrieve sensitive corporate data, amplifyi...
Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models
Large language models LLMs remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints gradually. These attacks target different harm categories like malware generation, harassment, or fraud through distinct conversational approaches...
A2AS: Agentic AI Runtime Security and Self-Defense
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It defines security boundaries, authenticates prompts, applies...
A Survey on Agentic Security: Applications, Threats and Defenses
The rapid shift from passive LLMs to autonomous LLM-agents marks a new paradigm in cybersecurity. While these agents can act as powerful tools for both offensive and defensive operations, the very agentic context introduces a new class of inherent security risks. In this work we present the first...
Defending against database ransomware attacks
How attackers exploit exposed databases for extortion—and the defenses that work...
