Whale Song Code

During the Cold War, the US Navy tried to make a secret code out of whale song. The basic plan was to develop coded messages from recordings of whales, dolphins, sea lions, and seals. The submarine would broadcast the noises and a computer--the Combo Signal Recognizer CSR--would detect the specif...

Friday Squid Blogging: Searching for the Colossal Squid

A cruise ship is searching for the colossal squid. 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...

Using AI-Generated Legislative Amendments as a Delaying Technique

Canadian legislators proposed 19,600 amendments--almost certainly AI-generated--to a bill in an attempt to delay its adoption. I wrote about many different legislative delaying tactics in A Hackers Mind, but this is a new one...

Friday Squid Blogging: The Awfulness of Squid Fishing Boats

Its a pretty awful story. 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...

Drones and the US Air Force

Fascinating analysis of the use of drones on a modern battlefield--that is, Ukraine--and the inability of the US Air Force to react to this change. The F-35A certainly remains an important platform for high-intensity conventional warfare. But the Air Force is planning to buy 1,763 of the aircraft...

Burglars Using Wi-Fi Jammers to Disable Security Cameras

The arms race continues, as burglars are learning how to use jammers to disable Wi-Fi security cameras...

Friday Squid Blogging: New Plant Looks Like a Squid

Newly discovered plant looks like a squid. And its super weird: The plant, which grows to 3 centimetres tall and 2 centimetres wide, emerges to the surface for as little as a week each year. It belongs to a group of plants known as fairy lanterns and has been given the scientific name...

The Insecurity of Video Doorbells

Consumer Reports has analyzed a bunch of popular Internet-connected video doorbells. Their security is terrible. First, these doorbells expose your home IP address and WiFi network name to the internet without encryption, potentially opening your home network to online criminals. … Anyone who can...

LLM Prompt Injection Worm

Researchers have demonstrated a worm that spreads through prompt injection. Details: In one instance, the researchers, acting as attackers, wrote an email including the adversarial text prompt, which "poisons" the database of an email assistant using retrieval-augmented generation RAG, a way for...

Upcoming Speaking Engagements

This is a current list of where and when I am scheduled to speak: I’m speaking at the Munich Security Conference MSC 2024 in Munich, Germany, on Friday, February 16, 2024. I’m giving a keynote on “AI and Trust” at Generative AI, Free Speech, & Public Discourse. The symposium will be held at...

On Software Liabilities

Over on Lawfare, Jim Dempsey published a really interesting proposal for software liability: "Standard for Software Liability: Focus on the Product for Liability, Focus on the Process for Safe Harbor." Section 1 of this paper sets the stage by briefly describing the problem to be solved. Section ...

Teaching LLMs to Be Deceptive

Interesting research: "Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training": Abstract: Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given th...

A Self-Enforcing Protocol to Solve Gerrymandering

In 2009, I wrote: There are several ways two people can divide a piece of cake in half. One way is to find someone impartial to do it for them. This works, but it requires another person. Another way is for one person to divide the piece, and the other person to complain to the police, a judge, o...

Microsoft Executives Hacked

Microsoft is reporting that a Russian intelligence agency--the same one responsible for SolarWinds--accessed the email system of the companys executives. Beginning in late November 2023, the threat actor used a password spray attack to compromise a legacy non-production test tenant account and ga...

Friday Squid Blogging: Footage of Black-Eyed Squid Brooding Her Eggs

Amazing footage of a black-eyed squid Gonatus onyx carrying thousands of eggs. They tend to hang out about 6,200 feet below sea level. 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...

Voice Cloning with Very Short Samples

New research demonstrates voice cloning, in multiple languages, using samples ranging from one to twelve seconds. Research paper...

Pharmacies Giving Patient Records to Police without Warrants

Add pharmacies to the list of industries that are giving private data to the police without a warrant...

Upcoming Speaking Engagements

This is a current list of where and when I am scheduled to speak: Im speaking at the AI Summit New York on December 6, 2023. The list is maintained on this page...

Signal Will Leave the UK Rather Than Add a Backdoor

Totally expected, but still good to hear: Onstage at TechCrunch Disrupt 2023, Meredith Whittaker, the president of the Signal Foundation, which maintains the nonprofit Signal messaging app, reaffirmed that Signal would leave the U.K. if the countrys recently passed Online Safety Bill forced Signa...

Spyware Vendor Hacked

A Brazilian spyware app vendor was hacked by activists: In an undated note seen by TechCrunch, the unnamed hackers described how they found and exploited several security vulnerabilities that allowed them to compromise WebDetetive’s servers and access its user databases. By exploiting other flaws...

Detecting “Violations of Social Norms” in Text with AI

Researchers are trying to use AI to detect "social norms violations." Feels a little sketchy right now, but this is the sort of thing that AIs will get better at. Like all of these systems, anything but a very low false positive rate makes the detection useless in practice. News article...

Friday Squid Blogging: NIWA Annual Squid Survey

Results from the National Institute of Water and Atmospheric Research Limited annual squid survey: This year, the team unearthed spectacular large hooked squids, weighing about 15kg and sitting at 2m long, a Taningia--­which has the largest known light organs in the animal kingdom­--and a few...

The Inability to Simultaneously Verify Sentience, Location, and Identity

Really interesting "systematization of knowledge" paper: "SoK: The Ghost Trilemma" Abstract: Trolls, bots, and sybils distort online discourse and compromise the security of networked platforms. User identity is central to the vectors of attack and manipulation employed in these contexts. However...

Using Machine Learning to Detect Keystrokes

Researchers have trained a ML model to detect keystrokes by sound with 95% accuracy. "A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards" Abstract: With recent developments in deep learning, the ubiquity of microphones and the rise in online services via personal devices,...

Hacking AI Resume Screening with Text in a White Font

The Washington Post is reporting on a hack to fool automatic resume sorting programs: putting text in a white font. The idea is that the programs rely primarily on simple pattern matching, and the trick is to copy a list of relevant keywords--or the published job description--into the resume in a...

Friday Squid Blogging: Zaqistan Flag

The fictional nation of Zaqistan in Utah has a squid on its flag. 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...

Indirect Instruction Injection in Multi-Modal LLMs

Interesting research: "Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs": Abstract: We demonstrate how images and sounds can be used for indirect prompt and instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding t...

Disabling Self-Driving Cars with a Traffic Cone

You can disable a self-driving car by putting a traffic cone on its hood: The group got the idea for the conings by chance. The person claims a few of them walking together one night saw a cone on the hood of an AV, which appeared disabled. They werent sure at the time which came first; perhaps...

Friday Squid Blogging: Balloon Squid

Masayoshi Matsumoto is a "master balloon artist," and he made a squid and other animals. 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...

Friday Squid Blogging: Giggling Squid

Giggling Squid is a Thai chain in the UK. 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...

UPS Data Harvested for SMS Phishing Attacks

I get UPS phishing spam on my phone all the time. I never click on it, because its so obviously spam. Turns out that hackers have been harvesting actual UPS delivery data from a Canadian tracking tool for its phishing SMSs...

Friday Squid Blogging: Squid Can Edit Their RNA

This is just crazy: Scientists dont yet know for sure why octopuses, and other shell-less cephalopods including squid and cuttlefish, are such prolific editors. Researchers are debating whether this form of genetic editing gave cephalopods an evolutionary leg or tentacle up or whether the editing...

Friday Squid Blogging: Online Cephalopod Course

Atlas Obscura has a five-part online course on cephalopods, taught by squid biologist Dr. Sarah McAnulty. 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...

On the Poisoning of LLMs

Interesting essay on the poisoning of LLMs--ChatGPT in particular: Given that weve known about model poisoning for years, and given the strong incentives the black-hat SEO crowd has to manipulate results, its entirely possible that bad actors have been poisoning ChatGPT for months. We dont know...

FBI Disables Russian Malware

Reuters is reporting that the FBI "had identified and disabled malware wielded by Russias FSB security service against an undisclosed number of American computers, a move they hoped would deal a death blow to one of Russias leading cyber spying programs." The headline says that the FBI "sabotaged...

Large Language Models and Elections

Earlier this week, the Republican National Committee released a video that it claims was "built entirely with AI imagery." The content of the ad isnt especially novel--a dystopian vision of America under a second term with President Joe Biden--but the deliberate emphasis on the technology used to...

Research on AI in Adversarial Settings

New research: “Achilles Heels for AGI/ASI via Decision Theoretic Adversaries": As progress in AI continues to advance, it is important to know how advanced systems will make choices and in what ways they may fail. Machines can already outsmart humans in some domains, and understanding how to safe...

NetWire Remote Access Trojan Maker Arrested

From Brian Krebs: A Croatian national has been arrested for allegedly operating NetWire, a Remote Access Trojan RAT marketed on cybercrime forums since 2012 as a stealthy way to spy on infected systems and siphon passwords. The arrest coincided with a seizure of the NetWire sales website by the...

New National Cybersecurity Strategy

Last week, the Biden administration released a new National Cybersecurity Strategy summary here. There is lots of good commentary out there. Its basically a smart strategy, but the hard parts are always the implementation details. Its one thing to say that we need to secure our cloud...

Friday Squid Blogging: Studying the Colossal Squid

A survey of giant squid science. As usual, you can also use this squid post to talk about the security stories in the news that I havent covered. Read my blog posting guidelines here...

Upcoming Speaking Engagements

This is a current list of where and when I am scheduled to speak: Im speaking at Capricon, a four-day science fiction convention in Chicago. My talk is on "The Coming AI Hackers" and will be held Friday, February 3 at 1:00 PM. The list is maintained on this page...

Remote Vulnerabilities in Automobiles

This group has found a ton of remote vulnerabilities in all sorts of automobiles. Its enough to make you want to buy a car that is not Internet-connected. Unfortunately, that seems to be impossible...

Decarbonizing Cryptocurrencies through Taxation

Maintaining bitcoin and other cryptocurrencies causes about 0.3 percent of global CO2 emissions. That may not sound like a lot, but its more than the emissions of Switzerland, Croatia, and Norway combined. As many cryptocurrencies crash and the FTX bankruptcy moves into the litigation stage,...

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...

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...

As Long as We’re on the Subject of CAPTCHAs

There are these...

Hacking Boston’s CharlieCard

Interesting discussion of vulnerabilities and exploits against Bostons CharlieCard...

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 thats not vital for the functioning of the operating system. It doesnt affect files with extensions .exe, .dll, .lnk, .sys or .msi, and ignores sever...

LastPass Security Breach

The company was hacked, and customer information accessed. No passwords were compromised...

Facebook Fined $276M under GDPR

Facebook--Meta--was just fined $276 million USD for a data leak that included full names, birth dates, phone numbers, and location. Metas total fine by the Data Protection Commission is over $700 million. Total GDPR fines are over €2 billion EUR since 2018...