ARCHIVE
Security News
-
Hiding Capabilities in AI Models
Interesting research: “AI Models Can Provably Hide Arbitrary Capabilities” Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities…
SRC // Schneier on Security -
Copenhagen University Breach Compromises Data on Half a Million People
Hackers have stolen personal information on over 520,000 people from the University of Copenhagen
SRC // Infosecurity Magazine -
Samsung TVs without mics may listen through soundbars, researcher says
TVs without a built-in microphone may use a connected soundbar or Bluetooth microphone to listen to the room.
SRC // Malwarebytes Labs -
First ISC2 AI Security Certification Expected for Early 2027
ISC2 is seeking 3000 volunteers to enrol to a pilot exam phase for its upcoming AI security certification
SRC // Infosecurity Magazine -

From federal SOCs to Talos: Ryan Fetterman on practical security research
What does it mean to be "blue collar" for the blue team? Ryan Fetterman discusses the realities of detection engineering, and shares his philosophy on building a career in security…
SRC // Cisco Talos Intelligence -
Watchdog Urges Police and Fire Service to Improve Cybersecurity
UK police forces and fire and rescue services have been urged to strengthen cybersecurity as rising cyber threats outpace current defenses
SRC // Infosecurity Magazine -

Japanese virtual desktop cloud hacked so hard it asks to be banned
CEO admits service used for foreign exchange trading had holes company was slow to fix
SRC // The Register — Security -

So Many AI Security Benchmarks, but None Tell the Whole Story
Measuring artificial intelligence model security gets complex, fast, thanks to a growing patchwork of benchmarks targeting different variables in the equation. But none replace testing against your own code and…
SRC // Dark Reading -

Worm armed 42 GitHub repos by hiding a payload too big to fail
Payload blobs measuring 12.9 to 13.7 MB were large enough to evade GitHub code search
SRC // The Register — Security -

Risks & Rewards: How AI Is Redefining the CISO’s Role
Nvidia security executive Mark Weatherford says CISOs must help business leaders weigh AI's pros and cons, and ensure those deploying it own the risks.
SRC // Dark Reading