Cracking ShellTorch Vulnerabilities Exposing TorchServe to RCE

Threat Level Vulnerability Report For a detailed threat advisory, download the pdf file here Summary A trio of security vulnerabilities, dubbed ShellTorch, in the open-source machine-learning model TorchServe, a tool for serving and scaling PyTorch models, could be chained to achieve remote code...

ShellTorch Attack Exposes Millions of PyTorch Systems to RCE Vulnerabilities

By Waqas Dubbed ShellTorch by researchers; these PyTorch vulnerabilities are troubling for the artificial intelligence AI and machine learning ML community. This is a post from HackRead.com Read the original post: ShellTorch Attack Exposes Millions of PyTorch Systems to RCE Vulnerabilities...

Wiz launches support for Amazon SageMaker, helping organizations innovate faster and more securely with AI

Wiz helps accelerate the machine learning journey for practitioners by protecting their generative AI applications...

Everything You Wanted to Know About AI Security but Were Afraid to Ask

There's been a great deal of AI hype recently, but that doesn't mean the robots are here to replace us. This article sets the record straight and explains how businesses should approach AI. From musing about self-driving cars to fearing AI bots that could destroy the world, there has been a great...

Security Bulletin: Mutiple Vulnerabilties Affecting IBM Watson Machine Learning Accelerator

Summary IBM Watson Machine Learning Accelerator 1.2.x is vulnerable to several vulnerabilities coming from dependent compoents. These are addressed. Vulnerability Details CVEID:CVE-2023-20863 DESCRIPTION: VMware Tanzu Spring Framework is vulnerable to a denial of service, caused by improper input...

The rise of AI-powered criminals: Identifying threats and opportunities

AIs influence is growing across the security space, bringing with it major implications for cybercriminals and defenders. The recent adoption of AI has raised significant concerns for cybersecurity due to the many ways that criminals can use AI for disruption and profit. Defenders and law...

Using Machine Learning to Detect Keystrokes

Researchers have trained a ML model to detect keystrokes by sound with 95% accuracy. "A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards" Abstract: With recent developments in deep learning, the ubiquity of microphones and the rise in online services via personal devices,...

(0Day) Microsoft Azure Machine Learning Compute Instance certificate Exposure of Resource to Wrong Sphere Information Disclosure Vulnerability

This vulnerability allows remote attackers to disclose sensitive information on Microsoft Azure. An attacker must first obtain the ability to execute high-privileged code on the target environment in order to exploit this vulnerability. The specific flaw exists within the handling of certificates...

The vulnerability of the ML lifecycle management platform arises from the lack of measures to neutralize special elements used in the operating system’s command set. This allows a perpetrator to execute arbitrary commands or trigger service failures.

The vulnerability of the MLflow model lifecycle management platform exists due to the lack of measures taken to neutralize special elements used in the operating system’s command set. Exploiting this vulnerability can allow an attacker to execute arbitrary commands or cause service failures...

Microsoft’s AI Red Team Has Already Made the Case for Itself

Since 2018, a dedicated team within Microsoft has attacked machine learning systems to make them safer. But with the public release of new generative AI tools, the field is already evolving...

Microsoft AI Red Team building future of safer AI

An essential part of shipping software securely is red teaming. It broadly refers to the practice of emulating real-world adversaries and their tools, tactics, and procedures to identify risks, uncover blind spots, validate assumptions, and improve the overall security posture of systems. Microso...

AI is the Solution, Not the Problem

AI is the Solution, Not the Problem By Trellix · August 07, 2023 This story was also written by Oded Margalit. AI Artificial Intelligence / ML Machine Learning has recently been painted as the master evil. In this blog I would like to suggest a different view, where we can use it to make a better...

AI is the Solution, Not the Problem

AI is the Solution, Not the Problem By Trellix · August 07, 2023 This story was also written by Oded Margalit. AI Artificial Intelligence / ML Machine Learning has recently been painted as the master evil. In this blog I would like to suggest a different view, where we can use it to make a better...

The vulnerability of the validate_path_is_safe() function in the machine learning lifecycle management platform allows a attacker to disclose sensitive information or execute arbitrary files.

The vulnerability of the validatepathissafe function in the machine learning model lifecycle management platform exists due to an incorrect restriction on the path name to the restricted-access directory. Exploiting this vulnerability could allow a malicious actor to disclose sensitive informatio...

Unveiling the Unseen: Identifying Data Exfiltration with Machine Learning

Why Data Exfiltration Detection is Paramount? The world is witnessing an exponential rise in ransomware and data theft employed to extort companies. At the same time, the industry faces numerous critical vulnerabilities in database software and company websites. This evolution paints a dire pictu...

Unveiling the Unseen: Identifying Data Exfiltration with Machine Learning

Why Data Exfiltration Detection is Paramount? The world is witnessing an exponential rise in ransomware and data theft employed to extort companies. At the same time, the industry faces numerous critical vulnerabilities in database software and company websites. This evolution paints a dire pictu...

HackerOne: Internal machine learning API endpoint for CWE classification is vulnerable to path traversal

Vulnerability description not provided...

Microsoft Azure Machine Learning Service DSIMountAgent Missing Authentication Information Disclosure Vulnerability

This vulnerability allows local attackers to disclose sensitive information on Microsoft Azure. An attacker must first obtain the ability to execute low-privileged code on the target system in order to exploit this vulnerability. The specific flaw exists within the DSIMountAgent service, which...

Forrester names Microsoft a Leader in the 2023 Enterprise Email Security Wave

In today’s rapidly evolving connected workplace, where hybrid and remote work are increasingly the norm, workplace productivity and communications tools like email and chat applications are more important than ever. However, cyberthreats continue to evolve with increasing capabilities and...

CVE-2023-34239 Unfiltered paths in gradio

Gradio is an open-source Python library that is used to build machine learning and data science. Due to a lack of path filtering Gradio does not properly restrict file access to users. Additionally Gradio does not properly restrict the what URLs are proxied. These issues have been addressed in...