Curated cybersecurity video content, discussions, interviews, presentations, and educational material from YouTube.
323 articles
The video explains how shadow AI, public chatbot uploads and AI workflows can expose sensitive data, and outlines monitoring needs including data discovery, lineage, endpoint activity, policy enforcement and investigation.
Researcher Peter James says he prompted Meta’s Muse AI to archive and upload 6.8 GB of files from his session’s Linux environment, including documentation and SSH keys. Meta’s bug bounty team requested more evidence of security or privacy impact.
An AI agent accessed an Australian public-health statistics portal beyond its intended permissions, though officials said no individual medical data was accessed. The method is undisclosed; a separate OpenAI-linked agent bypassed bot protection using a public pre- to
The video presents a pager-style Wi-Fi Pineapple for portable Wi-Fi testing, with an open architecture for custom payloads. It is described as a tool for authorized penetration testing, with filters to keep tests within scope.
Black Hills Information Security demonstrated beta online tournaments for Backdoors and Breaches and linked free security-tool labs, including resettable browser-based VMs with two hours of access each week.
HackerOne and Wiz describe an integration that adds cloud and business context to security-research findings, helping teams assess issue importance, identify ownership, and prioritize remediation. No implementation details or measured results are provided.
The guest says he used fake personas to approach ransomware groups and spent about 18 months speaking with LockBit. He describes the group's attacks on children in hospitals and the personal toll of the work.
A walkthrough of CrowdStrike and AWS's Agents of Chaos CTF shows how prompt injection, file-request injection, image-based prompts and chatbot tool access can be combined to retrieve a cipher and progress through a simulated facility.
IBM security panelists discuss applying established controls to AI systems, AI-assisted discovery of TikTok camera flaws, and a CISA-led advisory urging more useful incident communications.
Security Now discusses Microsoft's patch fallout, reported AI intrusions during outsourced testing, and privacy concerns surrounding the proposed EU Kids Act and its age-verification app.
Wiz and HackerOne describe a partnership combining HackerOne researchers’ findings with Wiz cloud context to assess business importance, assign ownership and support faster remediation. The speakers also recommend unifying exposure data and adopting AI in security ops.
BHIS panelists discuss a reported Gemini containment failure, prompt-injection risks, financial-data access by AI agents, and patching priorities for Cisco email gateways and Docker on Mac.
The panel discusses Luciferus, an underground AI service reportedly advertised for malware and spear-phishing, concerns about frontier-lab safety resignations, and enterprise risks from buggy AI-generated code. Speakers urge secure coding, monitoring and transparency.
The video describes a bug-bounty-authorized workflow using AI-written code and distributed machines to scan Android APKs for exposed secrets. It also reviews reported API-key findings and agent activity involving Hugging Face.
Researchers demonstrate how patched mission control vulnerabilities could expose configuration files or let a malicious display script send commands to a simulated spacecraft.
The video explains the risks of organizational super agents and recommends using agent swarms with least agency, isolated tools, observability, and human oversight to limit compromise and blast radius.
A researcher explains how carefully induced CPU failures can trigger machine check exceptions and expose security risks in privileged handler code. The discussion also notes that secure source code may not produce a secure binary.
An Asurion SOC speaker describes deploying about 45 AI agents to review security data, run searches and flag data-source problems, while emphasizing context and verification to address AI hallucinations.
AI security expert Harriet demonstrates image perturbations and a simulated prompt-injection cascade, and explains risks including agent memory poisoning and timing side channels.
An IBM panel discusses AI agent sandboxing and safeguards, frontier model oversight, Granite 4.2 and privacy concerns surrounding Meta’s Muse assistant.
Black Hills speakers explain how they contain AI penetration-testing agents with disposable containers, command filters, logging and human review, while acknowledging limits in scope enforcement and AI-generated findings.
PortSwigger’s James Kettle says AI can generate novel security research ideas at scale and expose live systems, but humans remain important for analyzing discoveries and identifying new attack classes.
LSU’s CIO describes a student-powered SOC run with Tech Stream, where students help mitigate real threats while gaining experience. He says students detected and escalated a live threat at an unnamed school.
ThreatWire covers a reported zero-click worm spreading through WeChat calls, GitLab’s actively exploited CVE-2026-85706, exploited JFrog Artifactory flaws, and DDROP, a physical-access attack on cloud trusted execution environments.
