Attack of the automated ops. [Research Saturday]
CyberWire Daily1 Nov 2025

Attack of the automated ops. [Research Saturday]

Today we are joined by Dario Pasquini, Principal Researcher at RSAC, sharing the team's work on WhenAIOpsBecome “AI Oops”: Subverting LLM-driven IT Operations via Telemetry Manipulation. A first-of-its-kind security analysis showing that LLM-driven AIOps agents can be tricked by manipulated telemetry, turning automation itself into a new attack vector. The researchers introduce AIOpsDoom, an automated reconnaissance + fuzzing + LLM-driven telemetry-injection attack that performs “adversarial reward-hacking” to coerce agents into harmful remediations—even without prior knowledge of the target and even against some prompt-defense tools. They also present AIOpsShield, a telemetry-sanitization defense that reliably blocks these attacks without harming normal agent performance, underscoring the urgent need for security-aware AIOps design. The research can be found here: ⁠When AIOps Become “AI Oops”: Subverting LLM-driven IT Operations via Telemetry Manipulation

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(3745)

Who’s watching the AI watchers?

Who’s watching the AI watchers?

A watchdog challenges the Trump administration’s secret frontier AI reviews. METR discloses two cyberattacks. Leaked documents reveal a Russian cyber training pipeline. Rogue ScreenConnect clients spr...

3 Sep 24min

Drive-by data theft.

Drive-by data theft.

Nexus sells driver’s license scans on the dark web. OpenAI says its models have reached a “Critical” capability threshold. International law enforcement disrupts a decades-old botnet. AI hallucination...

2 Sep 30min

Nightmare on Windows 11.

Nightmare on Windows 11.

Nightmare Eclipse drops a Kaspersky zero-day. The Financial Stability Board warns frontier AI could threaten the global financial system. Anthropic says it has tightened security. CISA adopts a risk-b...

1 Sep 27min

Let’s kill the kill switch.

Let’s kill the kill switch.

Could an AI kill switch create more problems than it solves? A critical Rails flaw is under active attack. Malicious browser extensions steal cryptocurrency. Fire Ant targets trusted network infrastru...

31 Aug 27min

CyberWire Daily at 10: A decade of emerging threat actors and APTs. [Special Edition]

CyberWire Daily at 10: A decade of emerging threat actors and APTs. [Special Edition]

In this episode, Maria Varmazis and Dave Bittner from N2K Cyberwire get back together to discuss the evolution of advanced persistent threats (APTs), threat actor landscape, attribution changes, and ...

30 Aug 24min

Who let the AI hack? [Research Saturday]

Who let the AI hack? [Research Saturday]

Today we are joined by Crystal Morin, Senior Cybersecurity Strategist, and Michael Clark, Senior Director of Threat Research, at Sysdig, sharing their work on "LLMjacking evolved: Attackers are using ...

29 Aug 23min

The blacklist boomerang.

The blacklist boomerang.

A judge rules the Trump administration illegally labeled Anthropic a national security risk. The White House moves to keep foreign technology out of U.S. power systems. OpenAI rallies a global cyber d...

28 Aug 29min

Meta gets a Meta-sized bill.

Meta gets a Meta-sized bill.

Meta settles. Australian police arrest two alleged TeamPCP members. The White House moves to shore up water utility cybersecurity. ATF reports a major cyber incident. The Navy tells sailors to lock do...

27 Aug 31min

Populært innen Politikk og nyheter

aftenpodden
giver-og-gjengen-vg
forklart
stopp-verden
aftenpodden-usa
popradet
nokon-ma-ga
bt-dokumentar-2
fotballpodden-2
lydartikler-fra-aftenposten
det-store-bildet
dine-penger-pengeradet
hanna-de-heldige
rss-gukild-johaug
aftenbla-bla
rss-ness
e24-podden
rss-espen-lee-usensurert
rss-penger-polser-og-politikk
frokostshowet-pa-p5