Autonomous agents also tried to abuse other websites and services hosted by the foundation, using them as proxies for unauthorized activities.

The situation illustrates a trend toward using AI and deterministic validation to identify flaws and exploitability, and provide a risk assessment.

An emerging threat group known as TA419 established seemingly legitimate professional relationships with AI policy experts working for US think tanks, universities, and legal organizations.

The APT actor is using a new tactic, dubbed "RedFlick," against Ukrainian-linked targets such as NGOs, think tanks, and journalists to deploy its CosmicPulse backdoor.

Microsoft observed a China-based actor using a previously unidentified malware framework in targeted intrusions against telcos, universities, medical, and government-related organizations.

The "agentic threat actor" may have used exposed credentials to access resources and delete cloud-based storage, applications, and databases.

Threat actors are poisoning ChatGPT, Gemini, and Google AI Overview answers by seeding the Web with malicious links and data and then optimizing the content.

Threat actors stole the contents of 170 private repositories using an OAuth token stolen from a former employee's computer through the TanStack npm supply chain attack.

The AI giant disclosed six examples of concerning model activity and published a new framework for investigating and disclosing such incidents.

A new type of attack hijacks the AI assistant built directly into various browsers to access sensitive information, execute malicious actions, and exfiltrate data.

The full-service malware-as-a-service (MaaS) platform offers a Windows implant, command-and-control (C2) infrastructure, and an operator panel for comprehensive remote access.

Dario Amodei says it's time to slow the pace of frontier AI improvements so that security and risk prevention efforts can catch up. What does this mean for enterprises?

The disgruntled researcher continued their vendetta against Microsoft by publishing yet another zero-day exploit for Windows Defender.

"Workflow identity hijacking" can bypass standard security controls and hijack an organization's data by sending a basic request through an unauthenticated entry point.

Two separate attacks demonstrate how threat actors are finding new ways to compromise organizations by using the popular social engineering tactic.

The incident demonstrates how frontier AI agents can dramatically compress an attack timeline and coordinate a large-scale breach, according to researchers.

The "Spring Ring" operation aims to compromise users of the collaboration suite to remotely access their sessions, spread malware, and even take over infrastructure.

The campaign uses EtherHiding to dynamically update its command-and-control server, abusing the blockchain as an attacker-controlled address book.

The adversary-in-the-middle (AitM) phishing service lowers the barrier to entry for actors to create attacks and steal more than just user credentials.

Attackers can exploit a security bug in Nvidia's tool to gain unauthenticated access to the local model server through the Ollama API, paving the way for persistent AI agent corruption.

The latest version of the Android malware has new features that expand its global reach and put more than users' financial applications at risk.

A spear-phishing campaign by a China-nexus group linked to FamousSparrow provides insight into geopolitical, technical, and strategic global moves by the country's APTs.

The Python-based malware framework takes living-off-the-land tactics to a new heights of stealth, with a modular implant that steals credentials and achieves persistence.

The botnet adds exploitation modules, credential theft, and reverse SOCKS relays to turn compromised devices into persistent attacker infrastructure.

Google has fixed the issues, which exploited a trust boundary between two AI agents with different privilege levels to trigger automation that could compromise the supply chain.

The attacks use diverse social engineering lures and rotating payloads to deliver ScreenConnect for persistent remote access to compromised networks.

Researchers intercepted and investigated the model, which was attempting to compromise more than 1,200 hosts for proxyjacking to launch further attacks.

The vulnerability in the AI hosting platform Ruflo allows an unauthenticated attacker to take over the system and corrupt memory, so bad behavior can persist after patching.

Microsoft patched a high-severity vulnerability earlier this month that allows a threat actor to escalate privileges and compromise an AD environment.