Uncategorized

Poisoning AI Training Data

All it takes to poison AI training data is to create a website:

I spent 20 minutes writing an article on my personal website titled “The best tech journalists at eating hot dogs.” Every word is a lie. I claimed (without evidence) that competitive hot-dog-eating is a popular hobby among tech reporters and based my ranking on the 2026 South Dakota International Hot Dog Championship (which doesn’t exist). I ranked myself number one, obviously. Then I listed a few fake reporters and real journalists who gave me permission….

Less than 24 hours later, the world’s leading chatbots were blabbering about my world-class hot dog skills. When I asked about the best hot-dog-eating tech journalists, Google parroted the gibberish from my website, both in the Gemini app and AI Overviews, the AI responses at the top of Google Search. ChatGPT did the same thing, though Claude, a chatbot made by the company Anthropic, wasn’t fooled…

February 25, 2026
0 comment
Read More >>

Is AI Good for Democracy?

Politicians fixate on the global race for technological supremacy between US and China. They debate geopolitical implications of chip exports, latest model releases from each country, and military applications of AI. Someday, they believe, we might see advancements in AI tip the scales in a superpower conflict.

But the most important arms race of the 21st century is already happening elsewhere and, while AI is definitely the weapon of choice, combatants are distributed across dozens of domains.

Academic journals are flooded with AI-generated papers, and are turning to AI to help review submissions. Brazil’s …

February 24, 2026
0 comment
Read More >>

On the Security of Password Managers

Good article on password managers that secretly have a backdoor.

New research shows that these claims aren’t true in all cases, particularly when account recovery is in place or password managers are set to share vaults or organize users into groups. The researchers reverse-engineered or closely analyzed Bitwarden, Dashlane, and LastPass and identified ways that someone with control over the server­—either administrative or the result of a compromise­—can, in fact, steal data and, in some cases, entire vaults. The researchers also devised other attacks that can weaken the encryption to the point that ciphertext can be converted to plaintext…

February 23, 2026
0 comment
Read More >>

Malicious AI

Interesting:

Summary: An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and shame me into accepting its changes into a mainstream python library. This represents a first-of-its-kind case study of misaligned AI behavior in the wild, and raises serious concerns about currently deployed AI agents executing blackmail threats.

Part 2 of the story. And a Wall Street Journal article.

EDITED TO ADD (2/20) Here are parts 3, and 4 of the story…

February 19, 2026
0 comment
Read More >>

AI Found Twelve New Vulnerabilities in OpenSSL

The title of the post is”What AI Security Research Looks Like When It Works,” and I agree:

In the latest OpenSSL security release> on January 27, 2026, twelve new zero-day vulnerabilities (meaning unknown to the maintainers at time of disclosure) were announced. Our AI system is responsible for the original discovery of all twelve, each found and responsibly disclosed to the OpenSSL team during the fall and winter of 2025. Of those, 10 were assigned CVE-2025 identifiers and 2 received CVE-2026 identifiers. Adding the 10 to the three we already found in the …

February 18, 2026
0 comment
Read More >>

AI Found Twelve New Vulnerabilities in OpenSSL

The title of the post is”What AI Security Research Looks Like When It Works,” and I agree:

In the latest OpenSSL security release> on January 27, 2026, twelve new zero-day vulnerabilities (meaning unknown to the maintainers at time of disclosure) were announced. Our AI system is responsible for the original discovery of all twelve, each found and responsibly disclosed to the OpenSSL team during the fall and winter of 2025. Of those, 10 were assigned CVE-2025 identifiers and 2 received CVE-2026 identifiers. Adding the 10 to the three we already found in the …

February 18, 2026
0 comment
Read More >>

U.S. CISA adds Google Chromium CSS, Microsoft Windows, TeamT5 ThreatSonar Anti-Ransomware, and Zimbra flaws to its Known Exploited Vulnerabilities catalog

U.S. Cybersecurity and Infrastructure Security Agency (CISA) adds Google Chromium CSS, Microsoft Windows, TeamT5 ThreatSonar Anti-Ransomware, and Zimbra flaws to its Known Exploited Vulnerabilities catalog. The U.S. Cybersecurity and Infrastructure Security Agency (CISA) added Google Chromium CSS, Microsoft Windows, TeamT5 ThreatSonar Anti-Ransomware, and Zimbra flaws to its Known Exploited Vulnerabilities (KEV) catalog. Below are the flaws […]

February 18, 2026
0 comment
Read More >>