Blog: December 2022 Archives

Friday Squid Blogging: Grounded Fishing Boat Carrying 16,000 Pounds of Squid

Rough seas are hampering efforts to salvage the boat:

The Speranza Marie, carrying 16,000 pounds of squid and some 1,000 gallons of diesel fuel, hit the shoreline near Chinese Harbor at about 2 a.m. on Dec. 15.

Six crew members were on board, and all were rescued without injury by another fishing boat.

[…]

However, large swells caused by the recent storm caused the Speranza Marie to pull loose from it anchored position and drift about 100 yards from from its original grounded location in Chinese Harbor, according to the Coast Guard.

As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered.

Read my blog posting guidelines here.

Tags:

Posted on December 30, 2022 at 5:56 PM • 117 Comments

Recovering Smartphone Voice from the Accelerometer

Yet another smartphone side-channel attack: “EarSpy: Spying Caller Speech and Identity through Tiny Vibrations of Smartphone Ear Speakers“:

Abstract: Eavesdropping from the user’s smartphone is a well-known threat to the user’s safety and privacy. Existing studies show that loudspeaker reverberation can inject speech into motion sensor readings, leading to speech eavesdropping. While more devastating attacks on ear speakers, which produce much smaller scale vibrations, were believed impossible to eavesdrop with zero-permission motion sensors. In this work, we revisit this important line of reach. We explore recent trends in smartphone manufacturers that include extra/powerful speakers in place of small ear speakers, and demonstrate the feasibility of using motion sensors to capture such tiny speech vibrations. We investigate the impacts of these new ear speakers on built-in motion sensors and examine the potential to elicit private speech information from the minute vibrations. Our designed system EarSpy can successfully detect word regions, time, and frequency domain features and generate a spectrogram for each word region. We train and test the extracted data using classical machine learning algorithms and convolutional neural networks. We found up to 98.66% accuracy in gender detection, 92.6% detection in speaker detection, and 56.42% detection in digit detection (which is 5X more significant than the random selection (10%)). Our result unveils the potential threat of eavesdropping on phone conversations from ear speakers using motion sensors.

It’s not great, but it’s an impressive start.

Tags: , , ,

Posted on December 30, 2022 at 7:18 AM • 57 Comments

Arresting IT Administrators

This is one way of ensuring that IT keeps up with patches:

Albanian prosecutors on Wednesday asked for the house arrest of five public employees they blame for not protecting the country from a cyberattack by alleged Iranian hackers.

Prosecutors said the five IT officials of the public administration department had failed to check the security of the system and update it with the most recent antivirus software.

The next step would be to arrest managers at software companies for not releasing patches fast enough. And maybe programmers for writing buggy code. I don’t know where this line of thinking ends.

Tags: , , ,

Posted on December 27, 2022 at 7:01 AM • 41 Comments

LastPass Breach

Last August, LastPass reported a security breach, saying that no customer information—or passwords—were compromised. Turns out the full story is worse:

While no customer data was accessed during the August 2022 incident, some source code and technical information were stolen from our development environment and used to target another employee, obtaining credentials and keys which were used to access and decrypt some storage volumes within the cloud-based storage service.

[…]

To date, we have determined that once the cloud storage access key and dual storage container decryption keys were obtained, the threat actor copied information from backup that contained basic customer account information and related metadata including company names, end-user names, billing addresses, email addresses, telephone numbers, and the IP addresses from which customers were accessing the LastPass service.

The threat actor was also able to copy a backup of customer vault data from the encrypted storage container which is stored in a proprietary binary format that contains both unencrypted data, such as website URLs, as well as fully-encrypted sensitive fields such as website usernames and passwords, secure notes, and form-filled data.

That’s bad. It’s not an epic disaster, though.

These encrypted fields remain secured with 256-bit AES encryption and can only be decrypted with a unique encryption key derived from each user’s master password using our Zero Knowledge architecture. As a reminder, the master password is never known to LastPass and is not stored or maintained by LastPass.

So, according to the company, if you chose a strong master password—here’s my advice on how to do it—your passwords are safe. That is, you are secure as long as your password is resilient to a brute-force attack. (That they lost customer data is another story….)

Fair enough, as far as it goes. My guess is that many LastPass users do not have strong master passwords, even though the compromise of your encrypted password file should be part of your threat model. But, even so, note this unverified tweet:

I think the situation at @LastPass may be worse than they are letting on. On Sunday the 18th, four of my wallets were compromised. The losses are not significant. Their seeds were kept, encrypted, in my lastpass vault, behind a 16 character password using all character types.

If that’s true, it means that LastPass has some backdoor—possibly unintentional—into the password databases that the hackers are accessing. (Or that @Cryptopathic’s “16 character password using all character types” is something like “P@ssw0rdP@ssw0rd.”)

My guess is that we’ll learn more during the coming days. But this should serve as a cautionary tale for anyone who is using the cloud: the cloud is another name for “someone else’s computer,” and you need to understand how much or how little you trust that computer.

If you’re changing password managers, look at my own Password Safe. Its main downside is that you can’t synch between devices, but that’s because I don’t use the cloud for anything.

News articles. Slashdot thread.

EDITED TO ADD: People choose lousy master passwords.

Tags: , , , ,

Posted on December 26, 2022 at 7:06 AM • 50 Comments

Critical Microsoft Code-Execution Vulnerability

A critical code-execution vulnerability in Microsoft Windows was patched in September. It seems that researchers just realized how serious it was (and is):

Like EternalBlue, CVE-2022-37958, as the latest vulnerability is tracked, allows attackers to execute malicious code with no authentication required. Also, like EternalBlue, it’s wormable, meaning that a single exploit can trigger a chain reaction of self-replicating follow-on exploits on other vulnerable systems. The wormability of EternalBlue allowed WannaCry and several other attacks to spread across the world in a matter of minutes with no user interaction required.

But unlike EternalBlue, which could be exploited when using only the SMB, or server message block, a protocol for file and printer sharing and similar network activities, this latest vulnerability is present in a much broader range of network protocols, giving attackers more flexibility than they had when exploiting the older vulnerability.

[…]

Microsoft fixed CVE-2022-37958 in September during its monthly Patch Tuesday rollout of security fixes. At the time, however, Microsoft researchers believed the vulnerability allowed only the disclosure of potentially sensitive information. As such, Microsoft gave the vulnerability a designation of “important.” In the routine course of analyzing vulnerabilities after they’re patched, Palmiotti discovered it allowed for remote code execution in much the way EternalBlue did. Last week, Microsoft revised the designation to critical and gave it a severity rating of 8.1, the same given to EternalBlue.

Tags: , , ,

Posted on December 22, 2022 at 7:01 AM • 3 Comments

Ukraine Intercepting Russian Soldiers’ Cell Phone Calls

They’re using commercial phones, which go through the Ukrainian telecom network:

“You still have a lot of soldiers bringing cellphones to the frontline who want to talk to their families and they are either being intercepted as they go through a Ukrainian telecommunications provider or intercepted over the air,” said Alperovitch. “That doesn’t pose too much difficulty for the Ukrainian security services.”

[…]

“Security has always been a mess, both in the army and among defence officials,” the source said. “For example, in 2013 they tried to get all the staff at the ministry of defence to replace our iPhones with Russian-made Yoto smartphones.

“But everyone just kept using the iPhone as a second mobile because it was much better. We would just keep the iPhone in the car’s glove compartment for when we got back from work. In the end, the ministry gave up and stopped caring. If the top doesn’t take security very seriously, how can you expect any discipline in the regular army?”

This isn’t a new problem and it isn’t a Russian problem. Here’s a more general article on the problem from 2020.

Tags: , , , , ,

Posted on December 21, 2022 at 7:09 AM • 53 Comments

Trojaned Windows Installer Targets Ukraine

Mandiant is reporting on a trojaned Windows installer that targets Ukrainian users. The installer was left on various torrent sites, presumably ensnaring people downloading pirated copies of the operating system:

Mandiant uncovered a socially engineered supply chain operation focused on Ukrainian government entities that leveraged trojanized ISO files masquerading as legitimate Windows 10 Operating System installers. The trojanized ISOs were hosted on Ukrainian- and Russian-language torrent file sharing sites. Upon installation of the compromised software, the malware gathers information on the compromised system and exfiltrates it. At a subset of victims, additional tools are deployed to enable further intelligence gathering. In some instances, we discovered additional payloads that were likely deployed following initial reconnaissance including the STOWAWAY, BEACON, and SPAREPART backdoors.

One obvious solution would be for Microsoft to give the Ukrainians Windows licenses, so they don’t have to get their software from sketchy torrent sites.

Tags: , , , , ,

Posted on December 20, 2022 at 7:30 AM • 13 Comments

How to Surrender to a Drone

The Ukrainian army has released an instructional video explaining how Russian soldiers should surrender to a drone:

“Seeing the drone in the field of view, make eye contact with it,” the video instructs. Soldiers should then raise their arms and signal they’re ready to follow.

After that the drone will move up and down a few meters, before heading off at walking pace in the direction of the nearest representatives of Ukraine’s army, it says.

The video also warns that the drone’s battery may run low, in which case it will head back to base and the soldiers should stay put and await a fresh one.

That one, too, should be met with eye contact and arms raised, it says.

Incredible.

Tags: , , ,

Posted on December 19, 2022 at 7:09 AM • 29 Comments

Apple Patches iPhone Zero-Day

The most recent iPhone update—to version 16.2—patches a zero-day vulnerability that “may have been actively exploited against versions of iOS released before iOS 15.1.”

News:

Apple said security researchers at Google’s Threat Analysis Group, which investigates nation state-backed spyware, hacking and cyberattacks, discovered and reported the WebKit bug.

WebKit bugs are often exploited when a person visits a malicious domain in their browser (or via the in-app browser). It’s not uncommon for bad actors to find vulnerabilities that target WebKit as a way to break into the device’s operating system and the user’s private data. WebKit bugs can be “chained” to other vulnerabilities to break through multiple layers of a device’s defenses.

Tags: , , , ,

Posted on December 16, 2022 at 7:04 AM • 15 Comments

A Security Vulnerability in the KmsdBot Botnet

Security researchers found a software bug in the KmsdBot cryptomining botnet:

With no error-checking built in, sending KmsdBot a malformed command­—like its controllers did one day while Akamai was watching­—created a panic crash with an “index out of range” error. Because there’s no persistence, the bot stays down, and malicious agents would need to reinfect a machine and rebuild the bot’s functions. It is, as Akamai notes, “a nice story” and “a strong example of the fickle nature of technology.”

Tags: ,

Posted on December 15, 2022 at 7:10 AM • 10 Comments

Recreating Democracy

Last week, I hosted a two-day workshop on recreating democracy.

The idea was to bring together people from a variety of disciplines who are all thinking about different aspects of democracy, less from a “what we need to do today” perspective and more from a blue-sky future perspective. My remit to the participants was this:

The idea is to start from scratch, to pretend we’re forming a new country and don’t have any precedent to deal with. And that we don’t have any unique interests to perturb our thinking. The modern representative democracy was the best form of government mid-eighteenth century politicians technology could invent. The twenty-first century is a very different place technically, scientifically, and philosophically. What could democracy look like if it were reinvented today? Would it even be democracy­—what comes after democracy?

Some questions to think about:

  • Representative democracies were built under the assumption that travel and communications were difficult. Does it still make sense to organize our representative units by geography? Or to send representatives far away to create laws in our name? Is there a better way for people to choose collective representatives?
  • Indeed, the very idea of representative government is due to technological limitations. If an AI system could find the optimal solution for balancing every voter’s preferences, would it still make sense to have representatives­—or should we vote for ideas and goals instead?
  • With today’s technology, we can vote anywhere and any time. How should we organize the temporal pattern of voting—­and of other forms of participation?
  • Starting from scratch, what is today’s ideal government structure? Does it make sense to have a singular leader “in charge” of everything? How should we constrain power­—is there something better than the legislative/judicial/executive set of checks and balances?
  • The size of contemporary political units ranges from a few people in a room to vast nation-states and alliances. Within one country, what might the smaller units be­—and how do they relate to one another?
  • Who has a voice in the government? What does “citizen” mean? What about children? Animals? Future people (and animals)? Corporations? The land?
  • And much more: What about the justice system? Is the twelfth-century jury form still relevant? How do we define fairness? Limit financial and military power? Keep our system robust to psychological manipulation?

My perspective, of course, is security. I want to create a system that is resilient against hacking: one that can evolve as both technologies and threats evolve.

The format was one that I have used before. Forty-eight people meet over two days. There are four ninety-minute panels per day, with six people on each. Everyone speaks for ten minutes, and the rest of the time is devoted to questions and comments. Ten minutes means that no one gets bogged down in jargon or details. Long breaks between sessions and evening dinners allow people to talk more informally. The result is a very dense, idea-rich environment that I find extremely valuable. (See the first ten comments below for details of the conversations.)

It was amazing event. Everyone participated. Everyone was interesting. (Details of the event—emerging themes, notes from the speakers—are in the comments.) It’s a week later and I am still buzzing with ideas. I hope this is only the first of an ongoing series of similar workshops.

Tags: ,

Posted on December 14, 2022 at 9:30 PM • 87 Comments

Obligatory ChatGPT Post

Seems like absolutely everyone everywhere is playing with Chat GPT.

So I did, too….

Write an essay in the style of Bruce Schneier on how ChatGPT will affect cybersecurity.

As with any new technology, the development and deployment of ChatGPT is likely to have a significant impact on the field of cybersecurity. In many ways, ChatGPT and other AI technologies hold great promise for improving the ability of organizations and individuals to defend against cyber threats. At the same time, however, the use of these technologies also raises important questions and concerns about the potential risks and challenges they may pose.

One of the key ways in which ChatGPT is likely to affect cybersecurity is by enabling organizations to more quickly and accurately identify potential security threats. With its ability to analyze vast amounts of data and identify patterns and trends that might be difficult for humans to spot, ChatGPT could be a valuable tool for detecting and responding to cyberattacks. This could be especially useful in the case of complex, coordinated attacks that might otherwise be difficult to identify and defend against.

Another potential benefit of ChatGPT in the realm of cybersecurity is its ability to improve communication and coordination among different organizations and agencies. By enabling these groups to more easily share information and work together to defend against cyber threats, ChatGPT could help to make the overall cybersecurity landscape more effective and efficient. This could be especially important in the case of large-scale attacks that require a coordinated response from multiple organizations.

Of course, as with any new technology, there are also potential risks and challenges associated with the use of ChatGPT in the field of cybersecurity. One key concern is the potential for ChatGPT to be used by malicious actors to conduct cyberattacks. By automating the process of planning and executing attacks, ChatGPT could make it easier for attackers to carry out sophisticated, coordinated attacks at a much faster pace than would be possible without AI. This could potentially make it more difficult for organizations and individuals to defend against such attacks.

Another potential risk is the possibility that ChatGPT could be used to create fake news or propaganda, which could be used to spread misinformation or confusion. In the context of cybersecurity, the spread of false information could potentially lead to confusion and panic, making it more difficult for organizations and individuals to respond effectively to cyber threats. Additionally, the use of ChatGPT to create fake news or propaganda could also undermine trust in information and communications systems, potentially undermining the overall security of these systems.

Overall, the development and deployment of ChatGPT is likely to have a significant impact on the field of cybersecurity. While ChatGPT and other AI technologies hold great promise for improving the ability of organizations and individuals to defend against cyber threats, it is important to carefully consider the potential risks and challenges they may pose, and to take appropriate measures to mitigate these risks. This may include implementing strict security protocols and safeguards to prevent unauthorized access to ChatGPT and other AI systems, as well as ongoing monitoring and evaluation to ensure that these technologies are being used in a safe and responsible manner.

Not bad. I don’t think I can retire, but I probably can go on vacation for a few days. And, of course, it’s going to get better…a lot better…and probably sooner than we expect. This is a big deal.

Tags: ,

Posted on December 13, 2022 at 7:17 AM • 82 Comments

Apple Is Finally Encrypting iCloud Backups

After way too many years, Apple is finally encrypting iCloud backups:

Based on a screenshot from Apple, these categories are covered when you flip on Advanced Data Protection: device backups, messages backups, iCloud Drive, Notes, Photos, Reminders, Safari bookmarks, Siri Shortcuts, Voice Memos, and Wallet Passes. Apple says the only “major” categories not covered by Advanced Data Protection are iCloud Mail, Contacts, and Calendar because “of the need to interoperate with the global email, contacts, and calendar systems,” according to its press release.

You can see the full list of data categories and what is protected under standard data protection, which is the default for your account, and Advanced Data Protection on Apple’s website.

With standard data protection, Apple holds the encryption keys for things that aren’t end-to-end encrypted, which means the company can help you recover that data if needed. Data that’s end-to-end encrypted can only be encrypted on “your trusted devices where you’re signed in with your Apple ID,” according to Apple, meaning that the company—or law enforcement or hackers—cannot access your data from Apple’s databases.

Note that this system doesn’t have the backdoor that was in Apple’s previous proposal, the one put there under the guise of detecting CSAM.

Apple says that it will roll out worldwide by the end of next year. I wonder how China will react to this.

Tags: , , ,

Posted on December 12, 2022 at 7:00 AM • 10 Comments

Hacking Trespass Law

This article talks about public land in the US that is completely surrounded by private land, which in some cases makes it inaccessible to the public. But there’s a hack:

Some hunters have long believed, however, that the publicly owned parcels on Elk Mountain can be legally reached using a practice called corner-crossing.

Corner-crossing can be visualized in terms of a checkerboard. Ever since the Westward Expansion, much of the Western United States has been divided into alternating squares of public and private land. Corner-crossers, like checker pieces, literally step from one public square to another in diagonal fashion, avoiding trespassing charges. The practice is neither legal nor illegal. Most states discourage it, but none ban it.

It’s an interesting ambiguity in the law: does checker trespass on white squares when it moves diagonally over black squares? But, of course, the legal battle isn’t really about that. It’s about the rights of property owners vs the rights of those who wish to walk on this otherwise-inaccessible public land.

This particular hack will be adjudicated in court. State court, I think, which means the answer might be different in different states. It’s not an example I discuss in my new book, but it’s similar to many I do discuss. It’s the act of adjudicating hacks that allows systems to evolve.

Tags: , , ,

Posted on December 9, 2022 at 3:02 PM • 34 Comments

Security Vulnerabilities in Eufy Cameras

Eufy cameras claim to be local only, but upload data to the cloud. The company is basically lying to reporters, despite being shown evidence to the contrary. The company’s behavior is so egregious that ReviewGeek is no longer recommending them.

This will be interesting to watch. If Eufy can ignore security researchers and the press without there being any repercussions in the market, others will follow suit. And we will lose public shaming as an incentive to improve security.

Update:

After further testing, we’re not seeing the VLC streams begin based solely on the camera detecting motion. We’re not sure if that’s a change since yesterday or something I got wrong in our initial report. It does appear that Eufy is making changes—it appears to have removed access to the method we were using to get the address of our streams, although an address we already obtained is still working.

Tags: , , , ,

Posted on December 9, 2022 at 7:11 AM • 14 Comments

Leaked Signing Keys Are Being Used to Sign Malware

A bunch of Android OEM signing keys have been leaked or stolen, and they are actively being used to sign malware.

Łukasz Siewierski, a member of Google’s Android Security Team, has a post on the Android Partner Vulnerability Initiative (AVPI) issue tracker detailing leaked platform certificate keys that are actively being used to sign malware. The post is just a list of the keys, but running each one through APKMirror or Google’s VirusTotal site will put names to some of the compromised keys: Samsung, LG, and Mediatek are the heavy hitters on the list of leaked keys, along with some smaller OEMs like Revoview and Szroco, which makes Walmart’s Onn tablets.

This is a huge problem. The whole system of authentication rests on the assumption that signing keys are kept secret by the legitimate signers. Once that assumption is broken, all bets are off:

Samsung’s compromised key is used for everything: Samsung Pay, Bixby, Samsung Account, the phone app, and a million other things you can find on the 101 pages of results for that key. It would be possible to craft a malicious update for any one of these apps, and Android would be happy to install it overtop of the real app. Some of the updates are from today, indicating Samsung has still not changed the key.

Tags: , , ,

Posted on December 8, 2022 at 7:08 AM • 17 Comments

The Decoupling Principle

This is a really interesting paper that discusses what the authors call the Decoupling Principle:

The idea is simple, yet previously not clearly articulated: to ensure privacy, information should be divided architecturally and institutionally such that each entity has only the information they need to perform their relevant function. Architectural decoupling entails splitting functionality for different fundamental actions in a system, such as decoupling authentication (proving who is allowed to use the network) from connectivity (establishing session state for communicating). Institutional decoupling entails splitting what information remains between non-colluding entities, such as distinct companies or network operators, or between a user and network peers. This decoupling makes service providers individually breach-proof, as they each have little or no sensitive data that can be lost to hackers. Put simply, the Decoupling Principle suggests always separating who you are from what you do.

Lots of interesting details in the paper.

Tags: , , , ,

Posted on December 7, 2022 at 7:04 AM • 25 Comments

CryWiper Data Wiper Targeting Russian Sites

Kaspersky is reporting on a data wiper masquerading as ransomware that is targeting local Russian government networks.

The Trojan corrupts any data that’s not vital for the functioning of the operating system. It doesn’t affect files with extensions .exe, .dll, .lnk, .sys or .msi, and ignores several system folders in the C:\Windows directory. The malware focuses on databases, archives, and user documents.

So far, our experts have seen only pinpoint attacks on targets in the Russian Federation. However, as usual, no one can guarantee that the same code won’t be used against other targets.

Nothing leading to an attribution.

News article.

Slashdot thread.

Tags: , , ,

Posted on December 6, 2022 at 7:04 AM • 13 Comments

CAPTCHA

This is an actual CAPTCHA I was shown when trying to log into PayPal.

As an actual human and not a bot, I had no idea how to answer. Is this a joke? (Seems not.) Is it a Magritte-like existential question? (It’s not a bicycle. It’s a drawing of a bicycle. Actually, it’s a photograph of a drawing of a bicycle. No, it’s really a computer image of a photograph of a drawing of a bicycle.) Am I overthinking this? (Definitely.) I stared at the screen, paralyzed, for way too long.

It’s probably the best CAPTCHA I have ever encountered; a computer would have just answered.

(In the end, I treated the drawing as a real bicycle and selected the appropriate squares…and it seemed to like that.)

Tags: ,

Posted on December 5, 2022 at 7:10 AM • 49 Comments

Existential Risk and the Fermi Paradox

We know that complexity is the worst enemy of security, because it makes attack easier and defense harder. This becomes catastrophic as the effects of that attack become greater.

In A Hacker’s Mind (coming in February 2023), I write:

Our societal systems, in general, may have grown fairer and more just over the centuries, but progress isn’t linear or equitable. The trajectory may appear to be upwards when viewed in hindsight, but from a more granular point of view there are a lot of ups and downs. It’s a “noisy” process.

Technology changes the amplitude of the noise. Those near-term ups and downs are getting more severe. And while that might not affect the long-term trajectories, they drastically affect all of us living in the short term. This is how the twentieth century could—statistically—both be the most peaceful in human history and also contain the most deadly wars.

Ignoring this noise was only possible when the damage wasn’t potentially fatal on a global scale; that is, if a world war didn’t have the potential to kill everybody or destroy society, or occur in places and to people that the West wasn’t especially worried about. We can’t be sure of that anymore. The risks we face today are existential in a way they never have been before. The magnifying effects of technology enable short-term damage to cause long-term planet-wide systemic damage. We’ve lived for half a century under the potential specter of nuclear war and the life-ending catastrophe that could have been. Fast global travel allowed local outbreaks to quickly become the COVID-19 pandemic, costing millions of lives and billions of dollars while increasing political and social instability. Our rapid, technologically enabled changes to the atmosphere, compounded through feedback loops and tipping points, may make Earth much less hospitable for the coming centuries. Today, individual hacking decisions can have planet-wide effects. Sociobiologist Edward O. Wilson once described the fundamental problem with humanity is that “we have Paleolithic emotions, medieval institutions, and godlike technology.”

Technology could easily get to the point where the effects of a successful attack could be existential. Think biotech, nanotech, global climate change, maybe someday cyberattack—everything that people like Nick Bostrom study. In these areas, like everywhere else in past and present society, the technologies of attack develop faster the technologies of defending against attack. But suddenly, our inability to be proactive becomes fatal. As the noise due to technological power increases, we reach a threshold where a small group of people can irrecoverably destroy the species. The six-sigma guy can ruin it for everyone. And if they can, sooner or later they will. It’s possible that I have just explained the Fermi paradox.

Tags: , ,

Posted on December 2, 2022 at 3:07 PM • 40 Comments

Sirius XM Software Vulnerability

This is new:

Newly revealed research shows that a number of major car brands, including Honda, Nissan, Infiniti, and Acura, were affected by a previously undisclosed security bug that would have allowed a savvy hacker to hijack vehicles and steal user data. According to researchers, the bug was in the car’s Sirius XM telematics infrastructure and would have allowed a hacker to remotely locate a vehicle, unlock and start it, flash the lights, honk the horn, pop the trunk, and access sensitive customer info like the owner’s name, phone number, address, and vehicle details.

Cars are just computers with four wheels and an engine. It’s no surprise that the software is vulnerable, and that everything is connected.

Tags: , ,

Posted on December 1, 2022 at 10:10 AM • 19 Comments

← November 2022CalendarJanuary 2023 →

Sidebar photo of Bruce Schneier by Joe MacInnis.