Category: Security technology

Auto Added by WPeMatico

Friday Squid Blogging: The Origin and Propagation of Squid

Posted on By infossl
academic papers, Security technology, squid, Uncategorized

New research (paywalled): Editor’s summary: Cephalopods are one of the most successful marine invertebrates in modern oceans, and they have a 500-million-year-old history. However, we know very little about their evolution because soft-bodied animals rarely fossilize. Ikegami et al. developed an approach to reveal squid fossils, focusing on their beaks, the sole hard component of … Read More “Friday Squid Blogging: The Origin and Propagation of Squid” »

My Latest Book: Rewiring Democracy

Posted on By infossl
books, deep, Rewiring Democracy, Schneier news, Security technology, Uncategorized

I am pleased to announce the imminent publication of my latest book, Rewiring Democracy: How AI will Transform our Politics, Government, and Citizenship: coauthored with Nathan Sanders, and published by MIT Press on October 21. Rewriting Democracy looks beyond common tropes like deepfakes to examine how AI technologies will affect democracy in five broad areas: … Read More “My Latest Book: Rewiring Democracy” »

GPT-4o-mini Falls for Psychological Manipulation

Posted on By infossl
academic papers, AI, psychology of security, Security technology, social engineering, Uncategorized

Interesting experiment: To design their experiment, the University of Pennsylvania researchers tested 2024’s GPT-4o-mini model on two requests that it should ideally refuse: calling the user a jerk and giving directions for how to synthesize lidocaine. The researchers created experimental prompts for both requests using each of seven different persuasion techniques (examples of which are … Read More “GPT-4o-mini Falls for Psychological Manipulation” »

Generative AI as a Cybercrime Assistant

Posted on By infossl
AI, cybercrime, extortion, Security technology, theft, Uncategorized

Anthropic reports on a Claude user: We recently disrupted a sophisticated cybercriminal that used Claude Code to commit large-scale theft and extortion of personal data. The actor targeted at least 17 distinct organizations, including in healthcare, the emergency services, and government and religious institutions. Rather than encrypt the stolen information with traditional ransomware, the actor … Read More “Generative AI as a Cybercrime Assistant” »

Indirect Prompt Injection Attacks Against LLM Assistants

Posted on By infossl
academic papers, AI, cyberattack, LLM, Security technology, threat models, Uncategorized

Really good research on practical attacks against LLM agents. “Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous” Abstract: The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware­—maliciously engineered prompts designed to manipulate LLMs to compromise the CIA triad of these … Read More “Indirect Prompt Injection Attacks Against LLM Assistants” »

1965 Cryptanalysis Training Workbook Released by the NSA

Posted on By infossl
cryptanalysis, history of cryptography, nsa, Security technology, Uncategorized

In the early 1960s, National Security Agency cryptanalyst and cryptanalysis instructor Lambros D. Callimahos coined the term “Stethoscope” to describe a diagnostic computer program used to unravel the internal structure of pre-computer ciphertexts. The term appears in the newly declassified September 1965 document Cryptanalytic Diagnosis with the Aid of a Computer, which compiled 147 listings … Read More “1965 Cryptanalysis Training Workbook Released by the NSA” »

We Are Still Unable to Secure LLMs from Malicious Inputs

Posted on By infossl
AI, cyberattack, LLM, Security technology, Uncategorized

Nice indirect prompt injection attack: Bargury’s attack starts with a poisoned document, which is shared to a potential victim’s Google Drive. (Bargury says a victim could have also uploaded a compromised file to their own account.) It looks like an official document on company meeting policies. But inside the document, Bargury hid a 300-word malicious … Read More “We Are Still Unable to Secure LLMs from Malicious Inputs” »