Schneier on Security

MARCH 7, 2023

This is a good survey on prompt injection attacks on large language models (like ChatGPT). Abstract: We are currently witnessing dramatic advances in the capabilities of Large Language Models (LLMs). This property, which makes them adaptable to even unseen tasks, might also make them susceptible to targeted adversarial prompting.

Paper 98

Paper 98

Security Affairs

NOVEMBER 24, 2022

RansomExx ransomware is the last ransomware in order of time to have a version totally written in the Rust programming language. The operators of the RansomExx ransomware (aka Defray777 and Ransom X) have developed a new variant of their malware, tracked as RansomExx2, that was ported into the Rust programming language.

Ransomware 99

Ransomware Encryption Manufacturing Government 99

Data Breach Today

AUGUST 22, 2022

Grandoreiro Banking Trojan Impersonates Mexican Government Officials Researchers uncovered a spear-phishing campaign targeting automotive and chemical manufacturers across the Spanish-speaking nations of Mexico and Spain.

Manufacturing 246

Manufacturing Phishing Government 246

Threatpost

JULY 26, 2021

Polyglot malware authors are increasingly using obscure programming languages to evade detection. Sprechen Sie Rust?

Security 135

Security 135

Information Matters

JANUARY 10, 2024

A new study just relased provides a detailed and technical overview of some key methods for reducing the risk of hallucinations in Large Language Models (LLMs).

Risk 52

Risk 52

Schneier on Security

JANUARY 7, 2021

Paper: “ Extracting Training Data from Large Language Models.” ” Abstract: It has become common to publish large (billion parameter) language models that have been trained on private datasets. We conclude by drawing lessons and discussing possible safeguards for training large language models.

Paper 144

Paper IT Cybersecurity 144

IBM Big Data Hub

APRIL 4, 2023

The AI Commentary feature is a generative AI built from a large language model that was trained on a massive corpus of language data. The world’s eyes were first opened to the power of large language models last November when a chatbot application dominated news cycles. The first thing they needed was domain expertise.

Metadata 88

Metadata IT Access 88

KnowBe4

JANUARY 4, 2023

Researchers at Check Point have shown that Large Language Models (LLMs) like OpenAI’s ChatGPT can be used to generate entire infection chains, beginning with a spear phishing email. The publicly available AI can be asked to write a targeted phishing email with perfect grammar.

Phishing 96

Phishing 96

Dark Reading

APRIL 7, 2023

Security teams need to find the best, most effective uses of large language models for defensive purposes.

Security 105

Security 105

Dark Reading

DECEMBER 6, 2022

Software firms and the National Security Agency urge developers to move to memory-safe programming languages to eliminate a major source of high-severity flaws.

Security 90

Security 90

KnowBe4

APRIL 13, 2023

The use of Large Language Models (LLMs) is the fine tuning AI engines like ChatGPT need to focus the scam email output to only effective content that results in a wave of new email scams.

Artificial Intelligence 88

Artificial Intelligence Security 88

Dark Reading

AUGUST 4, 2023

More tech giants are turning to the Rust programming language for its built-in memory safety and other security features.

Security 88

Security IT 88

Data Matters

JANUARY 3, 2024

The post Australia’s Digital Platform Regulators Release Working Papers on Risks and Harms Posed by Algorithms and Large Language Models appeared first on Data Matters Privacy Blog.

Paper 88

Paper Artificial Intelligence Risk Marketing 88

Dark Reading

MARCH 16, 2022

Natural language understanding is well-suited for scanning enterprise email to detect and filter out spam and other malicious content. Armorblox introduces a data loss prevention service to its email security platform using NLU.

Security 92

Security IT 92

Security Affairs

MARCH 28, 2022

The Hive ransomware gang ported its encryptor to the Rust programming language and implemented new features. The post Hive ransomware ports its encryptor to Rust programming language appeared first on Security Affairs. Follow me on Twitter: @securityaffairs and Facebook. Pierluigi Paganini. SecurityAffairs – hacking, ransomware).

Ransomware 86

Ransomware IT Communications Access 86

Data Breach Today

FEBRUARY 27, 2024

Study Shows Correlation Between Polite Language, Culture and LLM Output It pays to be nice, even to an inanimate chunk of code masquerading as a conversation partner, find Japanese researchers from Tokyo's Waseda University who investigated the performance of large language models under conditions ranging from rudeness to obsequiousness.

IT 256

IT 256

Dark Reading

JANUARY 26, 2021

Security Assertion Markup Language, a protocol most people use daily to log into applications, makes authentication easier for both admins and users. Here's what you need to know about SAML (and what it has to do with 'GoldenSAML').

Authentication 110

Authentication Security IT 110

Hanzo Learning Center

OCTOBER 3, 2023

This blog post aims to provide a clear and comprehensive overview of AI, Machine Learning (ML), and Large Language Models (LLMs) for a legal audience.

Artificial Intelligence 57

Artificial Intelligence Risk IT 57

Security Affairs

JANUARY 24, 2022

The maintainers of the Rust programming language fixed a high-severity flaw that could allow attackers to delete files and directories from a vulnerable system. The maintainers of the Rust programming language have released a security update for a high-severity vulnerability, tracked as CVE-2022-21658. through Rust 1.58.0,

Libraries 94

Libraries Access Security IT 94

Data Breach Today

MARCH 27, 2024

Crooks Are Recruiting AI Experts to Jailbreak Existing LLM Guardrails Cybercrooks are exploring ways to develop custom, malicious large language models after existing tools such as WormGPT failed to cater to their demands for advanced intrusion capabilities, security researchers say.

Security 300

Security 300

Dark Reading

NOVEMBER 17, 2022

Languages such as C and C++ rely too heavily on the programmer not making simple memory-related security errors.

Security 81

Security 81

Rocket Software

OCTOBER 1, 2020

It has also filtered down to the product level, including the creation of our recent open-source tool, Rocket Inclusive Language Scanner. Language has a profound impact on how we experience the world and ourselves. That’s why it’s important for language, including product language, to be inclusive.

File names 52

File names Customer Experience IT 52

Dark Reading

MARCH 12, 2021

Rust offers a safer programming language, but adoption is still a problem despite recent signs of increasing popularity.

108

108

KnowBe4

FEBRUARY 20, 2024

With the idea in mind to “audio-jack” a live call-based banking transaction, security researchers were successful in inserting cybercriminal-controlled account details.

Security 103

Security 103

IG Guru

MAY 26, 2022

The post NIST’s Cybersecurity Framework has become the common language for international cybersecurity via SC Computer appeared first on IG GURU. Check out the article.

Cybersecurity 85

Cybersecurity Risk Information Security Security 85

Schneier on Security

OCTOBER 21, 2022

Here’s the latest: a training-time attack that forces the model to exhibit a point of view: Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures.” Machine learning security is extraordinarily difficult because the attacks are so varied—and it seems that each new one is weirder than the next.

Mining 90

Mining Risk Communications IT 90

CILIP

JUNE 22, 2023

Welsh Culture and Language Celebrated at Yoto Carnegies 2023 The Blue Book of Nebo (Firefly Press), written and translated by Manon Steffan Ros, has won the Yoto Carnegie medal for Writing, and Saving Sorya: Chang and the Sun Bear, a graphic novel has received the Medal for Illustration.

Libraries 52

Libraries 52

Dark Reading

MAY 3, 2021

Researchers suggest a few reasons why operators rewrote Buer in an entirely new language

103

103

Security Affairs

APRIL 13, 2024

A critical vulnerability, named ‘ BatBadBut ’, impacts multiple programming languages, its exploitation can lead to command injection in Windows applications. The cybersecurity researcher RyotaK ( @ryotkak ) discovered a critical vulnerability, dubbed BatBadBut , which impacts multiple programming languages.

Data breaches 113

Data breaches Cybersecurity IT Information Security 113

ForAllSecure

SEPTEMBER 28, 2021

That’s why we’ve gone ahead and compiled a catalog of fuzz targets intended for Mayhem that’s written and compiled using several different languages (and architectures) like C/C++, Python, Go, Rust, Java and many others! Language Guides for the Fuzzme Targets. How Are Targets Organized in the Fuzzme Repository?

Access 52

Access IT Security 52

Data Breach Today

JANUARY 18, 2024

LeftoverLocals Affects Apple, AMD and Qualcomm Devices Researchers uncovered a critical vulnerability in graphic processing units of popular devices that could allow attackers to access data from large language models. They dubbed the vulnerability LeftoverLocals and said it affects the GPU frameworks of Apple, AMD and Qualcomm devices.

Access 317

Access IT 317

Data Breach Today

JANUARY 11, 2024

billion claim related to the NotPetya attack will change the language the insurance industry uses to exclude acts of war in its policies, and organizations need to consider how those changes affect risk, said attorney Peter Halprin. Merck & Co.'s s proposed settlement with insurers over a $1.4

Insurance 314

Insurance Risk IT 314

Data Breach Today

JANUARY 20, 2024

man avoided a recommended 15-year prison sentence for his role in BreachForums, once considered the largest English-language data breach forum of its kind. The Peekskill, N.Y.

Data breaches 307

Data breaches IT 307