Critical RCE Vulnerability Discovered in Ollama AI Infrastructure Tool

Cybersecurity researchers have detailed a now-patched security flaw affecting the Ollama open-source artificial intelligence AI infrastructure platform that could be exploited to achieve remote code execution. Tracked as CVE-2024-37032, the vulnerability has been codenamed Probllama by cloud...

The AI Debate: Google's Guidelines, Meta's GDPR Dispute, Microsoft's Recall Backlash

Google is urging third-party Android app developers to incorporate generative artificial intelligence GenAI features in a responsible manner. The new guidance from the search and advertising giant is an effort to combat problematic content, including sexual content and hate speech, created throug...

Securing AI Development in the Cloud: Navigating the Risks and Opportunities

AI-TRiSM - Trust, Risk and Security Management in the Age of AI Co-authored by Lara Sunday and Pojan Shahrivar As artificial intelligence AI and machine learning ML technologies continue to advance and proliferate, organizations across industries are investing heavily in these transformative...

Experts Find Flaw in Replicate AI Service Exposing Customers' Models and Data

Cybersecurity researchers have discovered a critical security flaw in an artificial intelligence AI-as-a-service provider Replicate that could have allowed threat actors to gain access to proprietary AI models and sensitive information. "Exploitation of this vulnerability would have allowed...

Researchers Uncover Flaws in Python Package for AI Models and PDF.js Used by Firefox

A critical security flaw has been disclosed in the llamacpppython Python package that could be exploited by threat actors to achieve arbitrary code execution. Tracked as CVE-2024-34359 CVSS score: 9.7, the flaw has been codenamed Llama Drama by software supply chain security firm Checkmarx. "If...

AI Python Package Flaw ‘Llama Drama’ Threatens Software Supply Chain

By Waqas The Llama Drama vulnerability in the Llama-cpp-Python package exposes AI models to remote code execution RCE attacks, enabling attackers to steal data. Currently, over 6,000 models are affected by this vulnerability. This is a post from HackRead.com Read the original post: AI Python...

New LLMjacking Attack Lets Hackers Hijack AI Models for Profit

By Deeba Ahmed Researchers uncover a novel cyberattack scheme called "LLMjacking" exploiting stolen cloud credentials to hijack powerful AI models. This article explores the implications of attackers leveraging large language models LLMs for malicious purposes and offers security recommendations...

PT-2024-25816

Name of the Vulnerable Software and Affected Versions llama-cpp-python affected versions not specified Description The issue is related to a Server Side Template Injection vulnerability in the llama-cpp-python package, which allows for remote code execution. This is due to the use of...

[SECURITY] Fedora 39 Update: onnx-1.14.0-9.fc39

onnx provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types...

Fedora: Security Advisory (FEDORA-2024-abe1e34fdb)

The remote host is missing an update for the SPDX-FileCopyrightText: 2024 Greenbone AG Some text descriptions might be excerpted from a referenced sources, and are Copyright C by the respective right holders. SPDX-License-Identifier: GPL-2.0-only ifdescription...

Ex-Google Engineer Arrested for Stealing AI Technology Secrets for China

The U.S. Department of Justice DoJ announced the indictment of a 38-year-old Chinese national and a California resident for allegedly stealing proprietary information from Google while covertly working for two China-based tech companies. Linwei Ding aka Leon Ding, a former Google engineer who was...

Over 100 Malicious AI/ML Models Found on Hugging Face Platform

As many as 100 malicious artificial intelligence AI/machine learning ML models have been discovered in the Hugging Face platform. These include instances where loading a pickle file leads to code execution, software supply chain security firm JFrog said. "The model's payload grants the attacker a...

Poisoning AI Models

New research into poisoning AI models: The researchers first trained the AI models using supervised learning and then used additional "safety training" methods, including more supervised learning, reinforcement learning, and adversarial training. After this, they checked if the AI still had hidde...

Rapid7’s Data-Centric Approach to AI in Belfast

Authored by Stuart Millar and Ryan Wilson. Rapid7 has expanded significantly in Belfast since establishing a presence back in 2014, resulting in the company's largest R&D hub outside the US with over 350 people spread across eight floors in our Chichester Street office. There is a wide range of...

Meta’s Purple Llama wants to test safety risks in AI models

Meta has announced Purple Llama, a project that aims to "bring together tools and evaluations to help the community build responsibly with open generative AI models." Generative Artificial Intelligence AI models have been around for years and their main function, compared to older AI models is th...

A Closer Look at ChatGPT's Role in Automated Malware Creation

This blog entry explores the effectiveness of ChatGPT's safety measures, the potential for AI technologies to be misused by criminal actors, and the limitations of current AI models...

4 Generative AI Security Benefits

It may be some time before generative AI security can autonomously mitigate cyber threats, but we’re already seeing early examples of how AI models can strengthen enterprise cybersecurity in powerful and transformative ways...

LLMs and Phishing

Heres an experiment being run by undergraduate computer science students everywhere: Ask ChatGPT to generate phishing emails, and test whether these are better at persuading victims to respond or click on the link than the usual spam. Its an interesting experiment, and the results are likely to...

Facebook ParlAI 1.0.0 Code Execution / Deserialization

Exploit Title: Facebook ParlAI 1.0.0 - Deserialization of Untrusted Data in parlai Date: 2021-09-11 Exploit Author: Abhiram V Vendor Homepage: https://parl.ai/ Software Link: https://github.com/facebookresearch/ParlAI Version: 1.1.0 Tested on: Linux CVE: CVE-2021-24040 References :...

parlai code issue vulnerability

parlai is used to train and evaluate AI models on a variety of publicly available conversational datasets. parlai suffers from a code issue vulnerability that stems from an insecure loading package that is vulnerable to YAML deserialization attacks in the affected version. An attacker could explo...