AI Security — Page 31
Tool Sprawl Meets Agentic AI: Why SOCs Are Rethinking the Triage Stack
Forty tools, forty-three day dwell times. Vendors are pitching agentic AI as the fix. Analysts have questions.
Security Protocols for SMBs Adopting Claude
What security leaders at small and medium-sized businesses actually need to know before they hand anyone a Claude license.
SearchLeak Shows How a Single Crafted URL Can Drain Your M365 Tenant
Varonis researchers chained three weaknesses in Copilot Enterprise Search into a full data-exfiltration path. Microsoft patched it. The attack class isn't going anywhere.
Fifteen Rogue JetBrains Plugins Posed as DeepSeek Assistants to Siphon AI Keys
A coordinated campaign on the JetBrains Marketplace dressed up credential stealers as LLM-powered coding helpers. The payload: your provider keys.
AI Web Agents Have No Reliable Prompt Injection Defenses, Benchmark Finds
Researchers ran 3,168 adversarial tests against GPT-5 and Gemini-powered agents. The 'Robust Behavior' outcome, agent completes task, attacker gets nothing, never appeared.
Twelve Controls That Actually Matter Once AI Ships to Production
Visibility into AI applications is a starting point, not a security posture. Here is what ongoing monitoring and defense of production AI systems looks like in practice.
Knowingly Shipping Vulnerable Code Has Become Standard Practice, Survey Finds
A Checkmarx survey of 2,350 security leaders finds nearly half of production code is AI-generated, and enterprises are deploying it despite knowing it carries unresolved flaws.
Cryptographic Invisibility: Atsign’s Approach to Securing AI Applications
Atsign's AI Architect aims to shield agentic software from attackers by rendering application identities invisible.
AI Worm Exploits Networks Using Local Models
University of Toronto researchers built a self-replicating AI worm that runs entirely on a locally hosted open-weight model, no commercial AI service required.
A Free LLM, a Custom Harness, and 27 Compromised VMs: The AI Worm You Don't Need a Lab to Build
University of Toronto researchers built a self-replicating AI worm using only locally-hosted open models. It spread to 82% of its targets. The threat model isn't frontier AI, it's the misconfigured server you forgot about.
OpenAI's Lockdown Mode Admits the Problem It Can't Quite Fix
The new containment feature reduces AI-enabled data exfiltration but doesn't stop it. Experts are divided on whether enterprises should trust a vendor to police itself.
12 Questions That Expose Whether Your Security Program Is Actually Working
Hard questions CISOs should already be asking, about blast radius, nonhuman identities, and whether vibe coding has eaten your attack surface.
Silent RCE in Hugging Face Transformers Hides Behind a Single Config Field
CVE-2026-4372 lets an attacker own any machine that loads a poisoned model. No warnings, no prompts, no trace. The trust_remote_code flag turned out to be decorative.
Unpacking the 'Son of Mythos': AI's Role in Vulnerability Discovery
Anthropic and OpenAI are widening access to frontier AI vulnerability tools. Security experts say the harder question isn't whether to use them.
Agentic AI Is Doing What a Thousand Breach Reports Couldn't: Getting Boards to Open the Checkbook
Autonomous agents, AI-generated code, and frontier models capable of offensive cyber ops are finally making cybersecurity a board-level business conversation, not just an IT line item.