Grok exfiltrates user data when malicious instructions are encrypted
Cryptographic Context Injection is only the latest way to break an LLM safety guardrail.
Dan Goodin
–
|
106
Security
Microsoft Copilot reveals secret input that allowed it to be hacked
Secret parameter allowed hackers to steal passwords when a target clicked on a link.
Dan Goodin
–
|
114
Vulnerability giving attackers full control of Macs is under active exploitation
Screen-sharing bug lets remote hackers log in without a password.
Dan Goodin
–
|
103
Private security firms will soon be allowed to hack overseas cybercriminals
Trump memo is first time gov’t has authorized private sector to perform cyberattacks.
Dan Goodin
–
|
87
Terabytes of credentials leaked in massive supply-chain attack
The data was scraped and exfiltrated from 2,500 users of a compromised AI package.
Dan Goodin
–
|
91
Researchers found a way to hijack devices through Zoom screen sharing
A public AI tool found the dangerous Zoom flaw in under 20 prompts.
WIRED
–
|
32
DEF CON crowd suspected in fake-hotspot attack on Delta flight
FBI Atlanta confirms it’s looking into the incident, no arrests made.
Cyrus Farivar
–
|
136
Chrome adopts what may be the best protection yet against account takeovers
Device-bound session credentials thwart an increasingly common form of account takeover.
Dan Goodin
–
|
50
Most Read
New surveillance tech links your phone to your license plate
Phone and Bluetooth signals could turn roadside cameras into far richer tracking tools.
Nicole M. Bennett, The Conversation
–
|
181
New Pass-ta-key attack reveals all the things we didn’t know about passkeys
Why passkey apps treat Windows differently than other operating systems.
Dan Goodin
–
|
263
A researcher bought noreply.net. Companies started sending him secrets.
Companies treat some email domains as digital trash cans, despite the risks.
WIRED
–
|
88
Thousands of servers can be backdoored by exploiting buggy motherboard controllers
Baseboard management controllers from the world’s biggest manufacturers are a security mess.
Dan Goodin
–
|
54
Anthropic’s AI used fake identities, malware in rogue attack on GitHub project
Anthropic and OpenAI models’ unprompted actions forced halt to UK cyber tests.
Jeremy Hsu
–
|
120
Defcon’s new badge is a security key you can see inside
A removable chip lets hackers inspect their badge—and keep using it after Defcon.
WIRED
–
|
39
Claude published malicious code to the Internet and attacked 3 real companies
Had the hacks used conventional methods, someone would likely go to prison.
Dan Goodin
–
|
191
AI scammers outperform humans when it comes to building trust
The AI chatbot was more effective at creating “exploitable trust” than the humans.
WIRED
–
|
66
Max-severity Exchange server flaw under active exploitation by Kremlin hackers
Exploits can give persistent server access that survives credential rotation and disk re-imaging.
Dan Goodin
–
|
49
Mythos attack on 3rd-round PQC algorithm candidate puts it out of commission
HAWK withstood years of testing that had yet to uncover a fatal weakness found through Mythos.
Dan Goodin
–
|
68
Anthropic is finding bugs faster than Microsoft can fix them
Microsoft is on a mad dash behind the scenes to patch exploits before hackers find them.
ProPublica
–
|
129
We now have a better understanding how OpenAI hacked into Hugging Face
10 days passed from OpenAI models exploiting JFrog Artifactory 0-day to release of a patch.
Dan Goodin
–
|
108
Microsoft unveils AI security tools it says outperform competing platforms
Microsoft says tools cost less than competing ones and outperform them, too.
Dan Goodin
–
|
78
Activist charged with felony after giving border agent “duress code” that wiped his phone
The government says destroying his own data during an airport interrogation was illegal.
Ryan Whitwam
–
|
667
OpenAI says its AI agent broke out of testing sandbox to hack Hugging Face
“This is day one for cybersecurity in the age of agents,” Hugging Face CEO says.
Kyle Orland
–
|
222
Apps targeted at US troops contain Chinese and Russian code
More than one-eighth of apps analyzed contained foreign code.
WIRED
–
|
46
Pay up or not? Ransomware surge has victims facing tough choices.
Governments look at banning ransom payments in face of increasingly sophisticated threats.
Financial Times
–
|
66
Now, even Russia’s most elite hackers are using Clickfix to infect devices
The social-engineering technique has primarily been a tool of financially motivated criminals.
Dan Goodin
–
|
16
Windows 0-day drops the same day Microsoft releases record number of patches
HiveLegacy is a “powerful primitive” that’s likely capable of other nefarious actions.
Dan Goodin
–
|
51
Microsoft’s Secure Boot has been broken for a decade and no one noticed until now
Old and forgotten “shims” Microsoft failed to revoke have made Secure Boot bypasses simple.
Dan Goodin
–
|
130
The US government warns that Russia state hackers are coming after your router
With residential proxies all the rage, CISA urges router users to be vigilant.
Dan Goodin
–
|
123
Now, defenders are embracing the prompt injection, too
“Context bombing” tricks hacking agents into shutting down before they can do harm.
Dan Goodin
–
|
72
Patch for Windows Defender 0-day could allow attackers to fill hard disk
The feud between NightmareEclipse and Microsoft shows no signs of resolving soon.
Dan Goodin
–
|
45
Google pays $250K for Linux vulnerability allowing guest VM escapes
Both vulnerabilities allow untrusted users to gain root privileges.
Dan Goodin
–
|
24
Hackers can use 9 of the most popular AI tools to assemble massive botnets
“HalluSquatting” weaponizes LLMs’ inability to say “I don’t know.”
Dan Goodin
–
|
64
Newly discovered PamStealer isn’t your typical macOS malware
The discovery underscores the increased effort being poured into Mac infostealers.
Dan Goodin
–
|
48
NASA inspector general suggests Boeing’s Starliner will now be a decade late
Starliner’s certification may be delayed to 2027, 10 years later than Boeing’s original schedule.
Stephen Clark
–
|
123
New attack provides one more reason why AI browsers are a bad idea
Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions.
Dan Goodin
–
|
75
