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...

Securing and governing the rise of autonomous agents​​

In this blog, you will hear directly from Corporate Vice President and Deputy Chief Information Security Officer CISO for Identity, Igor Sakhnov, about how to secure and govern autonomous agents. This blog is part of a new ongoing series where our Deputy CISOs share their thoughts on what is most...

Securing and governing the rise of autonomous agents​​

In this blog, you will hear directly from Corporate Vice President and Deputy Chief Information Security Officer CISO for Identity, Igor Sakhnov, about how to secure and govern autonomous agents. This blog is part of a new ongoing series where our Deputy CISOs share their thoughts on what is most...

AI Agents Need Data Integrity

Think of the Web as a digital territory with its own social contract. In 2014, Tim Berners-Lee called for a "Magna Carta for the Web" to restore the balance of power between individuals and institutions. This mirrors the original charter's purpose: ensuring that those who occupy a territory have ...

Agentic AI: How Autonomous Agents are Changing the Game

...

Webinar: What the Next Wave of AI Cyberattacks Will Look Like — And How to Survive

The AI revolution isn't coming. It's already here. From copilots that write our emails to autonomous agents that can take action without us lifting a finger, AI is transforming how we work. But here's the uncomfortable truth: Attackers are evolving just as fast. Every leap forward in AI gives bad...

Unpacking Qualys Agentic AI: Technical Insights into Its Architecture and Capabilities

Agentic AI revolutionizes how enterprise organizations leverage artificial intelligence by introducing systems designed to function as autonomous agents capable of planning, decision-making, and executing complex workflows with minimal human oversight. Unlike traditional AI, which often performs...

The Dark Side of LLMs Agent-Based Attacks for Complete Computer Takeover

The rapid adoption of Large Language Model LLM agents and multi-agent systems enables unprecedented capabilities in natural language processing and generation. However, these systems have introduced unprecedented security vulnerabilities that extend beyond traditional prompt injection attacks. Th...

Agent Safety Alignment Via Reinforcement Learning

The emergence of autonomous Large Language Model LLM agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to both user-initiated threats e.g., adversarial prompts and...

Reversing the Paradigm: Building AI-First Systems with Human Guidance

The relationship between humans and artificial intelligence is no longer science fiction -- it's a growing reality reshaping how we live and work. AI has moved beyond research labs into everyday life, powering customer service chats, personalizing travel, aiding doctors in diagnosis, and supporti...

Training RL Agents for Multi-Objective Network Defense Tasks

Open-ended learning OEL -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence AI agents to achieve robustness and generalization. However, despite promising results that demonstrate the benefits of...

COALESCE: Economic and Security Dynamics of Skill-Based Task Outsourcing among Team of Autonomous LLM Agents

The meteoric rise and proliferation of autonomous Large Language Model LLM agents promise significant capabilities across various domains. However, their deployment is increasingly constrained by substantial computational demands, specifically for Graphics Processing Unit GPU resources. This pape...

Security Concerns for Large Language Models: a Survey

Large Language Models LLMs such as GPT-4 and its recent iterations, Google's Gemini, Anthropic's Claude 3 models, and xAI's Grok have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities. In this survey, we provide a comprehensive...

Securing Agentic AI: a Comprehensive Threat Model and Mitigation Framework for Generative AI Agents

As generative AI GenAI agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act, often with minimal human oversight. This paper introduces ...

Using LLMs to Exploit Vulnerabilities

Interesting research: "Teams of LLM Agents can Exploit Zero-Day Vulnerabilities." Abstract: LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when given a description of the...

AIs Hacking Websites

New research: LLM Agents can Autonomously Hack Websites Abstract: In recent years, large language models LLMs have become increasingly capable and can now interact with tools i.e., call functions, read documents, and recursively call themselves. As a result, these LLMs can now function autonomous...

Gamifying machine learning for stronger security and AI models

To stay ahead of adversaries, who show no restraint in adopting tools and techniques that can help them attain their goals, Microsoft continues to harness AI and machine learning to solve security challenges. One area we’ve been experimenting on is autonomous systems. In a simulated enterprise...

Gamifying machine learning for stronger security and AI models

To stay ahead of adversaries, who show no restraint in adopting tools and techniques that can help them attain their goals, Microsoft continues to harness AI and machine learning to solve security challenges. One area we’ve been experimenting on is autonomous systems. In a simulated enterprise...