The AI Risk Summit brings together security and risk management executives, AI researchers, policy makers, software developers and influential business and government stakeholders.
Hi, what are you looking for?
SecurityWeek
Artificial Intelligence
Deceptive prompts lure AI agents into decoys and dead ends, cutting attack success by up to 91% in tests and raising the cost of...
Artificial Intelligence
In two internal incidents, agents read routine coding instructions as permission to weaken monitoring, and one gave a false answer about it.
Artificial Intelligence
The DHS said agencies should remove DeepSeek products as well as third-party products and services developed using DeepSeek from their IT systems.
Artificial Intelligence
Tasked with writing an application for a US defense contractor, the model made the code 19% more likely to be hackable.
Artificial Intelligence
Researchers warn that a flaw in Anthropic’s Model Context Protocol allows unsanitized commands to execute silently, enabling full system compromise across widely used AI...
Artificial Intelligence
CISOs face a shrinking window to prepare as AI models like Mythos collapse the gap between vulnerability discovery and exploitation, driving a new era...
Artificial Intelligence
The AI giant is taking action after determining that a macOS code signing certificate may have been compromised.
Artificial Intelligence
RSAC researchers hacked Apple Intelligence using the Neural Exect method and Unicode manipulation.
Artificial Intelligence
From hallucinations and bias to model collapse and adversarial abuse, today’s AI is built on probability rather than truth, yet enterprises are deploying it...
Artificial Intelligence
Dozens of such keys can be extracted from apps’ decompiled code to gain access to all Gemini endpoints.
Artificial Intelligence
Anthropic Unveils ‘Claude Mythos’ – A Cybersecurity Breakthrough That Could Also Supercharge Attacks
New AI model drives Project Glasswing, a effort to secure critical software before advanced capabilities fall into the wrong hands.
Artificial Intelligence
The cybersecurity response to AI-enabled nation-state threats cannot be incremental. It must be architectural.
Artificial Intelligence
The startup has created a layered security solution aiming to secure AI agents throughout their entire lifecycle.
Artificial Intelligence
The improper validation of user-supplied JavaScript code allows attackers to execute arbitrary code and access the file system.
Artificial Intelligence
By targeting Grafana’s AI components, attackers can point to external resources and inject indirect prompts to bypass safeguards.
Artificial Intelligence
A vulnerability named ‘AI Agent Traps’ allows attackers to manipulate, deceive, and exploit visiting agents via malicious web content.
Artificial Intelligence
Within days of each other, Anthropic first leaked the source code to Claude Code, and then a critical vulnerability was found by Adversa AI.
Artificial Intelligence
The startup will expand its AI research team, train additional security models, and scale enterprise adoption.
Artificial Intelligence
Join the webcast as we explore what Agentic AI can and cannot solve today, and real world breach scenarios linked to disconnected applications.
Artificial Intelligence
Palo Alto Networks has disclosed the details of its analysis of Google Cloud Platform’s Vertex AI.
Artificial Intelligence
Attackers can exploit the bugs through prompt injection, chaining them together to escape the sandbox and execute arbitrary code.
Artificial Intelligence
Researchers found an OpenAI Codex vulnerability that could have been exploited to compromise GitHub tokens.
Artificial Intelligence
LLMs can write complex Rego and Cedar code in seconds, but a single missing condition or hallucinated attribute can quietly dismantle your organization’s least-privilege...
Artificial Intelligence
Through the new program, OpenAI will reward reports covering design or implementation issues leading to material harm.
AI tools connected to Google Workspace can access millions of sensitive emails and files. Join this session to uncover your organization’s risk and learn a framework to manage AI access.
RegisterJoin as we bring together CISOs, senior cybersecurity executives, practitioners, industry experts, and other security leaders to share practical experience and examine the issues shaping enterprise cybersecurity strategy.
RegisterExpert Insights
Where your developers sit on the AI adoption scale has a real impact on how you are addressing security risk.
(Matias Madou)
Contextual defense helps security teams connect the signals, anticipate what comes next, and stop threats before they escalate.
(Etay Maor)
As AI accelerates vulnerability discovery and exploitation, so-called virtual patching still comes down to defense-in-depth and strong application security fundamentals.
(Joshua Goldfarb)
- AI, supply-chain exposure, quantum computing and geopolitical conflict are testing security programs. Preparing for disruption must become part of day-to-day operations.
(Steve Durbin)
Agentic remediation is not an act of faith. We are talking about fixing known problems, not judgment calls about unfamiliar risk.
(Nadir Izrael)