Securing agentic AI systems before they go rogue
In this Help Net Security video, Eoin Wickens, Director of Threat Intelligence at HiddenLayer, explores the security risks posed by agentic AI. He breaks down how agentic AI …
The hidden risks of LLM autonomy
Large language models (LLMs) have come a long way from the once passive and simple chatbots that could respond to basic user prompts or look up the internet to generate …
Why security teams cannot rely solely on AI guardrails
In this Help Net Security interview, Dr. Peter Garraghan, CEO of Mindgard, discusses their research around vulnerabilities in the guardrails used to protect large AI models. …
Review: AI Agents in Action
If you’re trying to make sense of how to actually build AI agents, not just talk about them, AI Agents in Action might be for you. About the author Michael Lanham, Lead …
Even the best safeguards can’t stop LLMs from being fooled
In this Help Net Security interview, Michael Pound, Associate Professor at the University of Nottingham shares his insights on the cybersecurity risks associated with LLMs. He …
SWE-agent: Open-source tool uses LLMs to fix issues in GitHub repositories
By connecting powerful language models like GPT-4o and Claude Sonnet 3.5 to real-world tools, the open-source tool SWE-agent allows them to autonomously perform complex tasks: …
When AI agents go rogue, the fallout hits the enterprise
In this Help Net Security interview, Jason Lord, CTO at AutoRABIT, discusses the cybersecurity risks posed by AI agents integrated into real-world systems. Issues like …
Package hallucination: LLMs may deliver malicious code to careless devs
LLMs’ tendency to “hallucinate” code packages that don’t exist could become the basis for a new type of supply chain attack dubbed …
The quiet data breach hiding in AI workflows
As AI becomes embedded in daily business workflows, the risk of data exposure increases. Prompt leaks are not rare exceptions. They are a natural outcome of how employees use …
Excessive agency in LLMs: The growing risk of unchecked autonomy
For an AI agent to “think” and act autonomously, it must be granted agency; that is, it must be allowed to integrate with other systems, read and analyze data, and have …
The rise of compromised LLM attacks
In this Help Net Security video, Sohrob Kazerounian, Distinguished AI Researcher at Vectra AI, discusses how the ongoing rapid adoption of LLM-based applications has already …
Two things you need in place to successfully adopt AI
Organizations should not shy away from taking advantage of AI tools, but they need to find the right balance between maximizing efficiency and mitigating organizational risk. …
Featured news
Resources
Don't miss
- North Korean hackers stole over $2 billion in cryptocurrency this year
- Rethinking AI security architectures beyond Earth
- DefectDojo: Open-source DevSecOps platform
- New system aims to keep people connected when networks fail
- Redis patches critical “RediShell” RCE vulnerability, update ASAP! (CVE-2025-49844)