Salt Typhoon’s Reach Continues to Grow

The US government has identified a ninth telecom that was successfully hacked by Salt Typhoon...

Prompt Injection Defenses Against LLM Cyberattacks

Interesting research: "Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks": Large language models LLMs are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defens...

Law Enforcement Deanonymizes Tor Users

The German police have successfully deanonymized at least four Tor users. It appears they watch known Tor relays and known suspects, and use timing analysis to figure out who is using what relay. Tor has written about this. Hacker News thread...

Cheating at Conkers

The men's world conkers champion is accused of cheating with a steel chestnut...

More Details on Israel Sabotaging Hezbollah Pagers and Walkie-Talkies

The Washington Post has a long and detailed story about the operation that's well worth reading alternate version here. The sales pitch came from a marketing official trusted by Hezbollah with links to Apollo. The marketing official, a woman whose identity and nationality officials declined to...

China Possibly Hacking US “Lawful Access” Backdoor

The Wall Street Journal is reporting that Chinese hackers Salt Typhoon penetrated the networks of US broadband providers, and might have accessed the backdoors that the federal government uses to execute court-authorized wiretap requests. Those backdoors have been mandated by law--CALEA--since...

California AI Safety Bill Vetoed

Governor Newsom has vetoed the state's AI safety bill. I have mixed feelings about the bill. There's a lot to like about it, and I want governments to regulate in this space. But, for now, it's all EU. Related, the Council of Europe treaty on AI is ready for signature. It'll be legally binding wh...

New Windows Malware Locks Computer in Kiosk Mode

Clever: A malware campaign uses the unusual method of locking users in their browser's kiosk mode to annoy them into entering their Google credentials, which are then stolen by information-stealing malware. Specifically, the malware "locks" the user's browser on Google's login page with no obviou...

Friday Squid Blogging: Squid Game Season Two Teaser

The teaser for Squid Game Season Two dropped. Blog moderation policy...

Security Researcher Sued for Disproving Government Statements

This story seems straightforward. A city is the victim of a ransomware attack. They repeatedly lie to the media about the severity of the breach. A security researcher repeatedly proves their statements to be lies. The city gets mad and sues the researcher. Lets hope the judge throws the case out...

SQL Injection Attack on Airport Security

Interesting vulnerability: …a special lane at airport security called Known Crewmember KCM. KCM is a TSA program that allows pilots and flight attendants to bypass security screening, even when flying on domestic personal trips. The KCM process is fairly simple: the employee uses the dedicated la...

NIST Releases First Post-Quantum Encryption Algorithms

From the Federal Register: After three rounds of evaluation and analysis, NIST selected four algorithms it will standardize as a result of the PQC Standardization Process. The public-key encapsulation mechanism selected was CRYSTALS-KYBER, along with three digital signature schemes:...

Leaked GitHub Python Token

Heres a disaster that didnt happen: Cybersecurity researchers from JFrog recently discovered a GitHub Personal Access Token in a public Docker container hosted on Docker Hub, which granted elevated access to the GitHub repositories of the Python language, Python Package Index PyPI, and the Python...

Upcoming Speaking Engagements

This is a current list of where and when I am scheduled to speak: Im speaking--along with John Bruce, the CEO and Co-founder of Inrupt--at the 18th Annual CDOIQ Symposium in Cambridge, Massachusetts, USA. The symposium runs from July 16 through 18, 2024, and my session is on Tuesday, July 16 at...

Upcoming Book on AI and Democracy

If youve been reading my blog, youve noticed that I have written a lot about AI and democracy, mostly with my co-author Nathan Sanders. I am pleased to announce that were writing a book on the topic. This isnt a book about deep fakes, or misinformation. This is a book about what happens when AI...

Model Extraction from Neural Networks

A new paper, "Polynomial Time Cryptanalytic Extraction of Neural Network Models," by Adi Shamir and others, uses ideas from differential cryptanalysis to extract the weights inside a neural network using specific queries and their results. This is much more theoretical than practical, but its a...

Espionage with a Drone

The US is using a World War II law that bans aircraft photography of military installations to charge someone with doing the same thing with a drone...

Friday Squid Blogging: Dana Squid Attacking Camera

Fantastic footage of a Dana squid attacking a camera at a depth of about a kilometer. 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...

Unredacting Pixelated Text

Experiments in unredacting text that has been pixelated...

Friday Squid Blogging: Squid Purses

Squid-shaped purses for sale. 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...

In Memoriam: Ross Anderson, 1956–2024

Last week, I posted a short memorial of Ross Anderson. The Communications of the ACM asked me to expand it. Heres the longer version. EDITED TO ADD 4/11: Two weeks before he passed away, Ross gave an 80-minute interview where he told his life story...

Maybe the Phone System Surveillance Vulnerabilities Will Be Fixed

It seems that the FCC might be fixing the vulnerabilities in SS7 and the Diameter protocol: On March 27 the commission asked telecommunications providers to weigh in and detail what they are doing to prevent SS7 and Diameter vulnerabilities from being misused to track consumers locations. The FCC...

Jailbreaking LLMs with ASCII Art

Researchers have demonstrated that putting words in ASCII art can cause LLMs--GPT-3.5, GPT-4, Gemini, Claude, and Llama2--to ignore their safety instructions. Research paper...

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...

Apple Announces Post-Quantum Encryption Algorithms for iMessage

Apple announced PQ3, its post-quantum encryption standard based on the Kyber secure key-encapsulation protocol, one of the post-quantum algorithms selected by NIST in 2022. Theres a lot of detail in the Apple blog post, and more in Douglas Stabilas security analysis. I am of two minds about this...

New Image/Video Prompt Injection Attacks

Simon Willison has been playing with the video processing capabilities of the new Gemini Pro 1.5 model from Google, and its really impressive. Which means a lot of scary new video prompt injection attacks. And remember, given the current state of technology, prompt injection attacks are impossibl...

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...

Code Written with AI Assistants Is Less Secure

Interesting research: "Do Users Write More Insecure Code with AI Assistants?": Abstract: We conduct the first large-scale user study examining how users interact with an AI Code assistant to solve a variety of security related tasks across different programming languages. Overall, we find that...

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...

Facial Recognition Systems in the US

A helpful summary of which US retail stores are using facial recognition, thinking about using it, or currently not planning on using it. This, of course, can all change without notice. Three years ago, I wrote that campaigns to ban facial recognition are too narrow. The problem here is...

Police Get Medical Records without a Warrant

More unconstrained surveillance: Lawmakers noted the pharmacies policies for releasing medical records in a letter dated Tuesday to the Department of Health and Human Services HHS Secretary Xavier Becerra. The letter--signed by Sen. Ron Wyden D-Ore., Rep. Pramila Jayapal D-Wash., and Rep. Sara...

Friday Squid Blogging: Influencer Accidentally Posts Restaurant Table QR Ordering Code

Another rare security + squid story: The woman--who has only been identified by her surname, Wang--was having a meal with friends at a hotpot restaurant in Kunming, a city in southwest China. When everyone’s selections arrived at the table, she posted a photo of the spread on the Chinese social...

Spying through Push Notifications

When you get a push notification on your Apple or Google phone, those notifications go through Apple and Google servers. Which means that those companies can spy on them--either for their own reasons or in response to government demands. Sen. Wyden is trying to get to the bottom of this: In a...

Security Analysis of a Thirteenth-Century Venetian Election Protocol

Interesting analysis: This paper discusses the protocol used for electing the Doge of Venice between 1268 and the end of the Republic in 1797. We will show that it has some useful properties that in addition to being interesting in themselves, also suggest that its fundamental design principle is...

FTC’s Voice Cloning Challenge

The Federal Trade Commission is running a competition "to foster breakthrough ideas on preventing, monitoring, and evaluating malicious voice cloning."...

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...

Coin Flips Are Biased

Experimental result: Many people have flipped coins but few have stopped to ponder the statistical and physical intricacies of the process. In a preregistered study we collected 350,757 coin flips to test the counterintuitive prediction from a physics model of human coin tossing developed by Pers...

Own Your Own Government Surveillance Van

A used government surveillance van is for sale in Chicago: So how was this van turned into a mobile spying center? Well, lets start with how it has more LCD monitors than a Counterstrike LAN party. They can be used to monitor any of six different video inputs including a videoscope camera. A...

Tracking Down a Suspect through Cell Phone Records

Interesting forensics in connection with a serial killer arrest: Investigators went through phone records collected from both midtown Manhattan and the Massapequa Park area of Long Island--two areas connected to a "burner phone" they had tied to the killings. In court, prosecutors later said the...

Typing Incriminating Evidence in the Memo Field

Dont do it: Recently, the manager of the Harvard Med School morgue was accused of stealing and selling human body parts. Cedric Lodge and his wife Denise were among a half-dozen people arrested for some pretty grotesque crimes. This part is also at least a little bit funny though: Over a three-ye...

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...

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...

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...

Russian Cyberwarfare Documents Leaked

Now this is interesting: Thousands of pages of secret documents reveal how Vulkans engineers have worked for Russian military and intelligence agencies to support hacking operations, train operatives before attacks on national infrastructure, spread disinformation and control sections of the...