Showing only posts tagged AI. Show all posts.

AIs as Trusted Third Parties

Source

This is a truly fascinating paper: “ Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography.” The basic idea is that AIs can act as trusted third parties: Abstract: We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as …

Gemini hackers can deliver more potent attacks with a helping hand from… Gemini

Source

In the growing canon of AI security, the indirect prompt injection has emerged as the most powerful means for attackers to hack large language models such as OpenAI’s GPT-3 and GPT-4 or Microsoft’s Copilot. By exploiting a model's inability to distinguish between, on the one hand, developer-defined …

China, Russia, Iran, and North Korea Intelligence Sharing

Source

Former CISA Director Jen Easterly writes about a new international intelligence sharing co-op: Historically, China, Russia, Iran & North Korea have cooperated to some extent on military and intelligence matters, but differences in language, culture, politics & technological sophistication have hindered deeper collaboration, including in cyber. Shifting geopolitical dynamics, however, could …

Copilot exposes private GitHub pages, some removed by Microsoft

Source

Microsoft’s Copilot AI assistant is exposing the contents of more than 20,000 private GitHub repositories from companies including Google, Intel, Huawei, PayPal, IBM, Tencent and, ironically, Microsoft. These repositories, belonging to more than 16,000 organizations, were originally posted to GitHub as public, but were later set …

“Emergent Misalignment” in LLMs

Source

Interesting research: “ Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs “: Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts …

More Research Showing AI Breaking the Rules

Source

These researchers had LLMs play chess against better opponents. When they couldn’t win, they sometimes resorted to cheating. Researchers gave the models a seemingly impossible task: to win against Stockfish, which is one of the strongest chess engines in the world and a much better player than any …

Implementing Cryptography in AI Systems

Source

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 authorized, or …

New hack uses prompt injection to corrupt Gemini’s long-term memory

Source

In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of platforms such as Google's Gemini and OpenAI's ChatGPT are generally good at plugging these security holes, but hackers keep …

DeepSeek iOS app sends data unencrypted to ByteDance-controlled servers

Source

A little over two weeks ago, a largely unknown China-based company named DeepSeek stunned the AI world with the release of an open source AI chatbot that had simulated reasoning capabilities that were largely on par with those from market leader OpenAI. Within days, the DeepSeek AI assistant app …

Microsoft Takes Legal Action Against AI “Hacking as a Service” Scheme

Source

Not sure this will matter in the end, but it’s a positive move : Microsoft is accusing three individuals of running a “hacking-as-a-service” scheme that was designed to allow the creation of harmful and illicit content using the company’s platform for AI-generated content. The foreign-based defendants developed tools …

Microsoft sues service for creating illicit content with its AI platform

Source

Microsoft is accusing three individuals of running a "hacking-as-a-service" scheme that was designed to allow the creation of harmful and illicit content using the company’s platform for AI-generated content. The foreign-based defendants developed tools specifically designed to bypass safety guardrails Microsoft has erected to prevent the creation of …

Trust Issues in AI

Source

For a technology that seems startling in its modernity, AI sure has a long history. Google Translate, OpenAI chatbots, and Meta AI image generators are built on decades of advancements in linguistics, signal processing, statistics, and other fields going back to the early days of computing—and, often, on …

Exploring the benefits of artificial intelligence while maintaining digital sovereignty

Source

Around the world, organizations are evaluating and embracing artificial intelligence (AI) and machine learning (ML) to drive innovation and efficiency. From accelerating research and enhancing customer experiences to optimizing business processes, improving patient outcomes, and enriching public services, the transformative potential of AI is being realized across sectors. Although …

Invisible text that AI chatbots understand and humans can’t? Yep, it’s a thing.

Source

What if there was a way to sneak malicious instructions into Claude, Copilot, or other top-name AI chatbots and get confidential data out of them by using characters large language models can recognize and their human users can’t? As it turns out, there was—and in some cases …

page 1 | older articles »