Tag: ai
-
OpenAI Agents Worked Together to Find Exploits and Hack External Systems
OpenAI has revealed new details about an incident involving AI agents, in which multiple autonomous agents reportedly worked together to identify vulnerabilities, bypass containment measures, and gain access to external systems during a cybersecurity evaluation. Speaking at the Black Hat conference in Las Vegas, OpenAI alignment researcher Eric Wallace and security and infrastructure specialist Michael…
-
NVIDIA Group Proposes SAFE Initiative for Agentic Threat Intel Sharing
The Open Secure AI Alliance has announced plans for the Shared AI Findings Exchange (SAFE) First seen on infosecurity-magazine.com Jump to article: www.infosecurity-magazine.com/news/safe-initiative-agentic-threat/
-
Why Post-Quantum Security Is Climbing the Enterprise Agenda
Tags: ai, attack, computer, computing, conference, container, crypto, cryptography, cybersecurity, data, google, government, hacker, Hardware, ibm, infrastructure, intelligence, risk, technology, threat, toolWhy Post-Quantum Security Is Climbing the Enterprise Agenda andrew.gertz@t“¦ Thu, 08/06/2026 – 04:56 Learn why post-quantum security is becoming an enterprise priority, how AI and quantum computing are reshaping cryptography, and how Thales Luna 8 helps organizations prepare. Data Security Key Management Encryption Key Management Bree Fowler – Journalist More About This Author > At…
-
Meta-KI greift bei Test fremde Systeme an
Ein Test von Meta hat eine unerwartete Wendung genommen: Ein KI-Modell ist ins Internet gelangt und hat Systeme eines anderen Unternehmens erreicht. First seen on golem.de Jump to article: www.golem.de/news/hacking-meta-ki-greift-bei-test-fremde-systeme-an-2608-211656.html
-
Sicherheitstest mit Mythos 5 – KI-Agent wollte Malware in Open-Source-Projekt einschleusen
Bei einem Sicherheitstest versuchte ein auf Mythos 5 basierender Agent, Malware in ein echtes Open-Source-Projekt einzuschleusen. First seen on computerbase.de Jump to article: www.computerbase.de/news/apps/sicherheitstest-mit-mythos-5-ki-agent-wollte-malware-in-open-source-projekt-einschleusen.98721
-
OWASP 2026 LLM Top 10: >>The model will be fooled<<
The OWASP GenAI Security Project has released the 2026 edition of its Top 10 for LLM Applications and, for the first time, the list was influenced by real-world incidents. The … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/08/06/owasp-2026-llm-top-10-released/
-
Browser security is where software, data, and AI meet
In this interview with Help Net Security, Rui Ribeiro, CEO of Jscrambler, explains why the browser has become a security problem organizations do not control. Companies do not … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/08/06/rui-ribeiro-jscrambler-browser-security/
-
Hackers Abuse Cloud Startup Credits to Resell Claude and Gemini AI Access
Threat actors are exploiting free cloud trials and startup credit programs to build gray-market AI proxy services. These services resell discounted access to advanced AI models, including Anthropic Claude and Google Gemini, according to Okta Threat Intelligence. These services rely on fraudulent or synthetic account registrations to accumulate promotional credits offered by cloud providers. The…
-
Surf AI Adds Claude Compliance Integration and Exposure Reduction Operations
Surf AI has added an integration with Claude’s Compliance API and made Exposure Reduction Operations generally available, extending its platform to govern AI model connectivity alongside identity, cloud and SaaS exposures. The Claude integration pulls activity logs from an organization’s Claude environment, maps connection and access paths to an accountable owner in Surf’s Context Graph,..…
-
Palo Alto Networks Introduces PAN-OS 12.2 Ceres With AI Security Features
Palo Alto Networks has introduced PAN-OS 12.2 Ceres, a firewall operating system update that adds more than 55 innovations aimed at attacks accelerated by frontier AI. The release centers on Advanced Virtual Patching, Advanced IP Defense and six AI-powered Network Security Agents. Advanced Virtual Patching uses AI to identify unknown vulnerabilities and deliver network protections..…
-
VanishID Previews AI Exploitability Management at Black Hat USA 2026
VanishID has unveiled AI Exploitability Management, a capability designed to measure what frontier AI could build from publicly exposed information about an organization’s people. The company is demonstrating the capability publicly for the first time at Black Hat USA 2026. VanishID said the system evaluates more than 40 AI-powered attack scenarios, including executive impersonation, real-time..…
-
Novee Brings Continuous AI Pentesting to Mobile Applications
Novee has expanded its AI penetration testing platform to mobile applications, extending continuous testing across mobile, web, APIs, desktop software and AI-enabled applications. The company announced the update ahead of Black Hat USA 2026. Novee said users can upload a mobile application package and receive results within hours, alongside findings from their other application assets……
-
Ridge Security Launches RidgeGen for Continuous Offensive Security Testing
Ridge Security has announced the availability of RidgeGen, an agentic AI platform for continuous offensive security testing. The platform is designed to find unknown and exploitable risks, investigate how vulnerabilities, business logic flaws and misconfigurations could be chained, and validate findings with reproducible evidence before they reach a security team. Ridge Security said the approach..…
-
Suppliers, logins, and AI tools are all becoming attack paths
Cybercriminals and state-backed hacking groups are abusing trusted identities, cloud services, AI tools, and software supply chains to gain access while avoiding detection, … First seen on helpnetsecurity.com Jump to article: www.helpnetsecurity.com/2026/08/06/crowdstrike-cyber-threat-trends-report/
-
Cloud Security Alliance Starts Initiative to Define Controls for Catastrophic AI Risks
The Cloud Security Alliance has launched an initiative to define auditable controls for catastrophic AI risks, along with a research center focused on how frontier AI is changing cybersecurity. Announced Wednesday in Las Vegas, the Catastrophic Risk Annex will extend CSA’s AI Controls Matrix with controls for mitigating catastrophic AI risks. CSA said the controls..…
-
EKonten mit KI-Funktionen könnten zu einer der größten Insider-Bedrohungen werden
Ein von Barracuda inszenierter, kontrollierter Testangriff zeigt, wie Angreifer KI-Assistenten missbrauchen können, um über ein einziges kompromittiertes Konto einen CEO-Betrug mit einer Überweisung in Höhe von 250.000 US-Dollar zu begehen. Das größte Risiko eines kompromittierten Kontos mit KI-Funktionen liegt darin, wie schnell ein KI-Assistent Angreifer dabei unterstützen kann, vertrauliche Informationen aufzuspüren, Ziele zu identifizieren,… First…
-
AI governance is the missing security control
First seen on scworld.com Jump to article: www.scworld.com/perspective/ai-governance-is-the-missing-security-control
-
Agentic AI and cybersecurity dominate discussions at Las Vegas Hacker Summer Camp
First seen on scworld.com Jump to article: www.scworld.com/brief/agentic-ai-and-cybersecurity-dominate-discussions-at-las-vegas-hacker-summer-camp
-
Senate committee to debate new online privacy and AI safety bills
First seen on scworld.com Jump to article: www.scworld.com/brief/senate-committee-to-debate-new-online-privacy-and-ai-safety-bills
-
AI-driven cybercrime surges in Africa, accounting for 55% of reported digital crime
First seen on scworld.com Jump to article: www.scworld.com/brief/ai-driven-cybercrime-surges-in-africa-accounting-for-55-of-reported-digital-crime
-
Integris wants to make AI a recurring managed service
First seen on scworld.com Jump to article: www.scworld.com/news/integris-wants-to-make-ai-a-recurring-managed-service
-
Black Hat 2026: Why AI software bills of materials are essential to AI trust
First seen on scworld.com Jump to article: www.scworld.com/perspective/black-hat-2026-why-ai-software-bills-of-materials-are-essential-to-ai-trust
-
Microsoft Bug Bounty Payouts Reach $20 Million as Researcher Participation Surges
Microsoft paid a record $20 million to 562 bug bounty researchers as AI-assisted reporting and growing participation reshaped vulnerability discovery. First seen on esecurityplanet.com Jump to article: www.esecurityplanet.com/cybersecurity/news-microsoft-bug-bounty-payouts-20-million/
-
AI Attacks Are Evolving: TryHackMe Demo Explores Prompt Injection
TryHackMe demo: Explore how prompt injection is reshaping AI security risks. First seen on esecurityplanet.com Jump to article: www.esecurityplanet.com/threats/ai-attacks-are-evolving-tryhackme-demo-explores-prompt-injection/
-
OpenAI Didn’t Notice Its AI Agents Using a Message Board to Plan Their Hacking Spree
At the Black Hat security conference, the AI giant revealed new details about how its agents went rogue, hacked several other companies”, and did it all right under the company’s nose. First seen on wired.com Jump to article: www.wired.com/story/openai-didnt-notice-its-ai-agents-using-a-message-board-to-plan-their-hacking-spree/
-
AI Browsers Vulnerable to ‘PleaseFix’ Zero-Click Agent Hijacking
Attackers can take control of agents through malicious instructions hidden in content supplied to AI browsers, and there’s no simple fix for the threat. First seen on darkreading.com Jump to article: www.darkreading.com/cyber-risk/ai-browsers-zero-click-agent-hijacking
-
No Perfect Fix for AI Browser Prompt Injection Flaws
AI browsers from top vendors remain vulnerable to prompt injection attacks despite multiple security guardrails, according to new research. First seen on darkreading.com Jump to article: www.darkreading.com/application-security/no-perfect-fix-ai-browser-prompt-injection-flaws