RedLine, Lumma, and Vidar adapted in 48 hours. Clawdbot's localhost trust model collapsed, plaintext memory files sit exposed ...
Moltbot is a security nightmare: 5 reasons to avoid using the viral AI agent right now ...
A Microsoft Visual Studio Code extension for Moltbot turns out to actually deliver a malware payload to unsuspecting users.
AI is no longer an emerging risk; it is now a central driver of offensive and defensive cyber capabilities. As organizations ...
Critical vulnerabilities in edge devices are continuing to be discovered by security researchers and rapidly targeted by attackers. Lately this includes a critical ...
Cybersecurity experts share insights on securing Application Programming Interfaces (APIs), essential to a connected tech world.
TEL AVIV, Israel, Jan. 19, 2026 /PRNewswire/ -- Adversa AI announced that its Adversa AI Agentic AI Security Platform has been named a winner in the 2026 BIG Innovation Awards in the Innovative ...
F5's Guardrails blocks prompts that attempt jailbreaks or injection attacks, and its AI Red Team automates vulnerability ...
Anthropic has launched Cowork with a known data exfiltration vulnerability that researchers reported in October 2025 but ...
Malicious Chrome extensions on the Chrome Web Store masquerading as productivity and security tools for enterprise HR and ERP ...
CrowdStrike's 2025 data shows attackers breach AI systems in 51 seconds. Field CISOs reveal how inference security platforms defend against prompt injection, model extraction, and 9 other runtime ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results