Inside the loop: Five AI attack frameworks that never ask permission
Five agentic offensive frameworks act in bursts of two to 25 seconds, and none enforces authorization in code. What ARTEX, CyberStrikeAI, Cairn, PentAGI, and…
Five agentic offensive frameworks act in bursts of two to 25 seconds, and none enforces authorization in code. What ARTEX, CyberStrikeAI, Cairn, PentAGI, and…
A CyberStrikeAI server spent 16 days in four AWS accounts using eight identities, and the CloudTrail record shows why six detection rules each caught only part…
Taking advantage of the anticipation for GTA 6, cybercriminals deploy various scams ranging from malware downloads and fake leaks to fraudulent stores and…
Blockchain complexities, such as attacker-deployed sweepers, hobble security controls designed to limit the damage of an exchange compromise.
This essay is adapted from a keynote speech delivered at the DEF CON 34 conference in Las Vegas on August 7, 2026. The essay originally appeared in CyberScoop.…
Kaspersky experts analyze a recent ransomware incident and discuss why the hypervisor layer remains difficult to monitor, what common access paths adversaries…
Since 2021, Project Zero has followed a “90 + 30” vulnerability disclosure policy, allowing vendors up to 90 days to remediate a vulnerability plus an extra 30…
This vulnerability allows remote attackers to escalate privileges on affected installations of SmarterTools SmarterMail. Authentication is required to exploit…
This vulnerability allows local attackers to escalate privileges on affected installations of TrendAI Vision One Security Agent. An attacker must first obtain…
This vulnerability allows local attackers to escalate privileges on affected installations of TrendAI Vision One Security Agent. An attacker must first obtain…
This vulnerability allows local attackers to escalate privileges on affected installations of TrendAI Vision One Security Agent. An attacker must first obtain…
This vulnerability allows local attackers to escalate privileges on affected installations of TrendAI Vision One Security Agent. An attacker must first obtain…
This vulnerability allows remote attackers to execute arbitrary code on affected installations of open62541. Authentication is required to exploit this…
This vulnerability allows remote attackers to delete arbitrary files on affected installations of ATEN eco DC. Authentication is required to exploit this…
This vulnerability allows network-adjacent attackers to execute arbitrary code on affected installations of Philips Hue Bridge. Authentication is not required…
This vulnerability allows network-adjacent attackers to bypass authentication on affected installations of Philips Hue Bridge. Authentication is not required…
This vulnerability allows remote attackers to execute arbitrary code on affected installations of OpenAI Codex. User interaction is required to exploit this…
Most organizations haven't sorted out their cryptographic estate enough to even know where they'd start with post-quantum cryptography (PQC).
Cybercriminals using agentic pen-testing tools is a proverbial genie out of the bottle at this point, so enterprises need to get a defense plan in place right…
The cybercriminals are retargeting law firms that refused to pay its first ransom, with a social engineering con aimed at stealing Microsoft access tokens.
Amy reflects on a formative college anthropology course that taught her the power of asking questions to bridge cultural gaps.
Microsoft Defender Research and the AI Red Team discuss how poisoned datasets and poisoned model checkpoints can trigger remote code execution and other…
Adyen’s Dino Dai Zovi shows how hardware security proven in payments can contain AI-driven attacks, even when vulnerabilities cannot be patched.
This is the first article in a series on cloud penetration testing. We'll cover the three cloud layers (External, Overlay, and Underlay), common architectures…