The next hot AI scam. [Research Saturday]
CyberWire Daily25 Feb 2023

The next hot AI scam. [Research Saturday]

Andy Patel from WithSecure Labs joins with Dave to discuss their study that demonstrates how GPT-3 can be misused through malicious and creative prompt engineering. The research looks at how this technology, GPT-3 and GPT-3.5, can be used to trick users into scams. GPT-3 is a user-friendly tool that employs autoregressive language to generate versatile natural language text using a small amount of input that could inevitably interest cybercriminals. The research is looking for possible malpractice from this tool, such as phishing content, social opposition, social validation, style transfer, opinion transfer, prompt creation, and fake news. The research can be found here: Creatively malicious prompt engineering

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

Episoder(3705)

The world's least private hackers.

The world's least private hackers.

Hackers target Thailand’s Ministry of Finance with an autonomous AI agent.A new industry alliance hopes to improve AI security. Golden Chickens lay four new malware families. GitHub and PyPI introduce...

27 Jul 27min

How sovereign is Europe's space industry? [T-Minus: Space-Cyber Briefing]

How sovereign is Europe's space industry? [T-Minus: Space-Cyber Briefing]

As space becomes an increasingly important part of global communications, national security, and critical infrastructure, European governments are confronting a difficulty: How much control do they ne...

26 Jul 24min

Cold lures, hot targets. [Research Saturday]

Cold lures, hot targets. [Research Saturday]

This week, we are joined by Ondrej Kubovič, Security Awareness Specialist from ESET, discussing their work on "FrostyNeighbor: Fresh mischief and digital shenanigans." Ondrej walks us through ESET's l...

25 Jul 17min

Laundry Bear gets the spin cycle.

Laundry Bear gets the spin cycle.

Laundry Bear snuffles through unpatched Zimbra Collaboration servers. The State Department puts visa restrictions on cybercriminals. Oracle drops a record 1,449 security patches. Researchers disclose ...

24 Jul 26min

Do not pass Go(ogle).

Do not pass Go(ogle).

Google gets a billion dollar fine from the EU. The White House considers sanctions against Chinese AI developers. The GAO criticizes overlap in cyber reporting regulations. The Feds warn of Iranian ag...

23 Jul 26min

The AI has entered the chat.

The AI has entered the chat.

GPT escapes the sandbox and hacks Huggingface. SolarWinds patches multiple critical flaws. CISA orders patching of a critical Langflow AI vulnerability. A Paidwork breach affects over 23 million users...

22 Jul 29min

The defense against the AI arts.

The defense against the AI arts.

Trump's latest AI leader resigns. The Army burns through its AI tokens. Scammers impersonate IC3 personnel.HollowGraph malware uses a compromised Microsoft 365 calendar for C2. Qilin ransomware target...

21 Jul 25min

Behind the friendly face.

Behind the friendly face.

Hugging Face reports an autonomous AI-powered breach. Ernst & Young discloses a client data breach. Attackers are actively exploiting a critical ServiceNow flaw. Ransomware gangs sharpen their tactics...

20 Jul 29min

Populært innen Politikk og nyheter

giver-og-gjengen-vg
aftenpodden
forklart
popradet
stopp-verden
rss-gukild-johaug
fotballpodden-2
aftenpodden-usa
hanna-de-heldige
dine-penger-pengeradet
rss-ness
aftenbla-bla
det-store-bildet
nokon-ma-ga
e24-podden
lydartikler-fra-aftenposten
unitedno
oppdatert
bt-dokumentar-2
liverpoolno-pausepraten