3024 matches found
The Signal Chat Leak and the NSA
US National Security Advisor Mike Waltz, who started the now-infamous group chat coordinating a US attack against the Yemen-based Houthis on March 15, is seemingly now suggesting that the secure messaging service Signal has security vulnerabilities. "I didn't see this loser in the group," Waltz...
Friday Squid Blogging: Squid Werewolf Hacking Group
In another rare squid/cybersecurity intersection, APT37 is also known as "Squid Werewolf." As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered...
Implementing Cryptography in AI Systems
Interesting research: "How to Securely Implement Cryptography in Deep Neural Networks." Abstract: The wide adoption of deep neural networks DNNs raises the question of how can we equip them with a desired cryptographic functionality e.g, to decrypt an encrypted input, to verify that this input is...
On Generative AI Security
Microsoft's AI Red Team just published "Lessons from Red Teaming 100 Generative AI Products." Their blog post lists "three takeaways," but the eight lessons in the report itself are more useful: 1. Understand what the system can do and where it is applied. 2. You don't have to compute gradients t...
Friday Squid Blogging: On Squid Brains
Interesting. Blog moderation policy...
CISA Under Trump
Jen Easterly is out as the Director of CISA. Read her final interview: There's a lot of unfinished business. We have made an impact through our ransomware vulnerability warning pilot and our pre-ransomware notification initiative, and I'm really proud of that, because we work on preventing somebo...
Zero-Day Vulnerability in Ivanti VPN
It's being actively exploited...
Hacking Digital License Plates
Not everything needs to be digital and "smart." License plates, for example: Josep Rodriguez, a researcher at security firm IOActive, has revealed a technique to “jailbreak” digital license plates sold by Reviver, the leading vendor of those plates in the US with 65,000 plates already sold. By...
Race Condition Attacks against LLMs
These are two attacks against the system components surrounding LLMs: We propose that LLM Flowbreaking, following jailbreaking and prompt injection, joins as the third on the growing list of LLM attack types. Flowbreaking is less about whether prompt or response guardrails can be bypassed, and mo...
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...
Texas Sues GM for Collecting Driving Data without Consent
Texas is suing General Motors for collecting driver data without consent and then selling it to insurance companies: From CNN: In car models from 2015 and later, the Detroit-based car manufacturer allegedly used technology to "collect, record, analyze, and transmit highly detailed driving data...
Hacking Scientific Citations
Some scholars are inflating their reference counts by sneaking them into metadata: Citations of scientific work abide by a standardized referencing system: Each reference explicitly mentions at least the title, authors names, publication year, journal or conference name, and page numbers of the...
Friday Squid Blogging: 1994 Lair of Squid Game
I didnt know: In 1994, Hewlett-Packard released a miracle machine: the HP 200LX pocket-size PC. In the depths of the device, among the MS-DOS productivity apps built into its fixed memory, there lurked a first-person maze game called Lair of Squid. … In Lair of Squid, youre trapped in an underwat...
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...
The US Is Banning Kaspersky
This move has been coming for a long time. The Biden administration on Thursday said it’s banning the company from selling its products to new US-based customers starting on July 20, with the company only allowed to provide software updates to existing customers through September 29. The ban--th...
Breaking the M-209
Interesting paper about a German cryptanalysis machine that helped break the US M-209 mechanical ciphering machine. The paper contains a good description of how the M-209 works...
Using AI for Political Polling
Public polling is a critical function of modern political campaigns and movements, but it isnt what it once was. Recent US election cycles have produced copious postmortems explaining both the successes and the flaws of public polling. There are two main reasons polling fails. First, nonresponse...
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: 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...
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...
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...
No, Toothbrushes Were Not Used in a Massive DDoS Attack
The widely reported story last week that 1.5 million smart toothbrushes were hacked and used in a DDoS attack is false. Near as I can tell, a German reporter talking to someone at Fortinet got it wrong, and then everyone else ran with it without reading the German text. It was a hypothetical, whi...
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...
Friday Squid Blogging—18th Anniversary Post: New Species of Pygmy Squid Discovered
Theyre Ryukyuan pygmy squid Idiosepius kijimuna and Hannans pygmy squid Kodama jujutsu. The second one represents an entire new genus. As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered. And, yes, this is the eighteenth anniversary of...
OpenAI Is Not Training on Your Dropbox Documents—Today
Theres a rumor flying around the Internet that OpenAI is training foundation models on your Dropbox documents. Heres CNBC. Heres Boing Boing. Some articles are more nuanced, but theres still a lot of confusion. It seems not to be true. Dropbox isnt sharing all of your documents with OpenAI. But...
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...
On the Cybersecurity Jobs Shortage
In April, Cybersecurity Ventures reported on extreme cybersecurity job shortage: Global cybersecurity job vacancies grew by 350 percent, from one million openings in 2013 to 3.5 million in 2021, according to Cybersecurity Ventures. The number of unfilled jobs leveled off in 2022, and remains at 3...
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...
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...
The US Is Spying on the UN Secretary General
The Washington Post is reporting that the US is spying on the UN Secretary General. The reports on Guterres appear to contain the secretary generals personal conversations with aides regarding diplomatic encounters. They indicate that the United States relied on spying powers granted under the...
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...
On the Need for an AI Public Option
Artificial intelligence will bring great benefits to all of humanity. But do we really want to entrust this revolutionary technology solely to a small group of US tech companies? Silicon Valley has produced no small number of moral disappointments. Google retired its "dont be evil" pledge before...
Friday Squid Blogging: “Mediterranean Beef Squid” Hoax
The viral video of the "Mediterranean beef squid"is a hoax. Its not even a deep fake; its a plastic toy. 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 Food Poisoning
University of Connecticut basketball player Jordan Hawkins claims to have suffered food poisoning from calamari the night before his NCAA finals game. The restaurant disagrees: On Sunday, a Mastros employee politely cast doubt on the idea that the restaurant might have caused the illness, citing...
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...
A Hacker’s Mind News
My latest book continues to sell well. Its ranking hovers between 1,500 and 2,000 on Amazon. Its been spied in airports. Reviews are consistently good. I have been enjoying giving podcast interviews. It all feels pretty good right now. You can order a signed book from me here. For those of you in...
ChatGPT Privacy Flaw
OpenAI has disabled ChatGPTs privacy history, almost certainly because they had a security flaw where users were seeing each others histories...
Friday Squid Blogging: New Species of Vampire Squid Lives 3,000 Feet below Sea Level
At least, it seems to be a new species. 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...