PT-2025-36532

Name of the Vulnerable Software and Affected Versions: MONAI versions up to and including 1.5.0 Description: MONAI is an AI toolkit for health care imaging. The software contains insecure model loading methods that can trigger a deserialization vulnerability, potentially leading to code execution...

"Energon": Unveiling Transformers from GPU Power and Thermal Side-Channels

Transformers have become the backbone of many Machine Learning ML applications, including language translation, summarization, and computer vision. As these models are increasingly deployed in shared Graphics Processing Unit GPU environments via Machine Learning as a Service MLaaS, concerns aroun...

LoRA-Leak: Membership Inference Attacks against LoRA Fine-Tuned Language Models

Language Models LMs typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation LoRA has gained the most widespread use in LM fine-tuning due to its lightweight computational cost...

The Hidden Weaknesses in AI SOC Tools that No One Talks About

If you're evaluating AI-powered SOC platforms, you've likely seen bold claims: faster triage, smarter remediation, and less noise. But under the hood, not all AI is created equal. Many solutions rely on pre-trained AI models that are hardwired for a handful of specific use cases. While that might...

Adversarial Text Generation with Dynamic Contextual Perturbation

Adversarial attacks on Natural Language Processing NLP models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically focus on word-level or local text segment alterations,...

Sylva: Tailoring Personalized Adversarial Defense in Pre-Trained Models Via Collaborative Fine-Tuning

Whitepaper called Sylva: Tailoring Personalized Adversarial Defense In Pre-Trained Models Via Collaborative Fine-Tuning...

Protocol-Agnostic and Data-Free Backdoor Attacks on Pre-Trained Models in RF Fingerprinting

While supervised deep neural networks DNNs have proven effective for device authentication via radio frequency RF fingerprinting, they are hindered by domain shift issues and the scarcity of labeled data. The success of large language models has led to increased interest in unsupervised pre-train...

Designing a Reliable Lateral Movement Detector Using a Graph Foundation Model

Foundation models have recently emerged as a new paradigm in machine learning ML. These models are pre-trained on large and diverse datasets and can subsequently be applied to various downstream tasks with little or no retraining. This allows people without advanced ML expertise to build ML...

CVE-2024-7764

Vanna-ai v0.6.2 is vulnerable to SQL Injection due to insufficient protection when generate_sql calls extract_sql on the LLM response. An attacker can insert a semicolon between a data field and their own command, causing extract_sql to remove LLM-generated SQL and execute the attacker’s command ...

Microsoft Azure GPT ALE palantirdemoacr Uncontrolled Search Path Element Remote Code Execution Vulnerability

This vulnerability allows remote attackers to execute arbitrary code on affected installations of Microsoft Azure GPT ALE. Authentication is not required to exploit this vulnerability. The specific flaw exists within the installation of Generative Pre-trained Transformer Active Learning Engine GP...

Yogurt Heist Reveals a Rampant Form of Online Fraud

Plus: “MFA bombing” attacks target Apple users, Israel deploys face recognition tech on Gazans, AI gets trained to spot tent encampments, and OSINT investigators find fugitive Amond Bundy...

SUSE SLES15 Security Update : kernel (Live Patch 26 for SLE 15 SP3) (SUSE-SU-2023:0339-1)

The remote SUSE Linux SLES15 host has a package installed that is affected by a vulnerability as referenced in the SUSE- SU-2023:0339-1 advisory. This update for the Linux Kernel 5.3.18-15030059101 fixes one issue. The following security issue was fixed: - CVE-2022-2602: Fixed a local privilege...

Ubuntu: Security Advisory (USN-5854-1)

The remote host is missing an update for the SPDX-FileCopyrightText: 2023 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...

New Study Uncovers Text-to-SQL Model Vulnerabilities Allowing Data Theft and DoS Attacks

A group of academics has demonstrated novel attacks that leverage Text-to-SQL models to produce malicious code that could enable adversaries to glean sensitive information and stage denial-of-service DoS attacks. "To better interact with users, a wide range of database applications employ AI...

New Study Uncovers Text-to-SQL Model Vulnerabilities Allowing Data Theft and DoS Attacks

A group of academics has demonstrated novel attacks that leverage Text-to-SQL models to produce malicious code that could enable adversaries to glean sensitive information and stage denial-of-service DoS attacks. "To better interact with users, a wide range of database applications employ AI...

SUSE SLES15: cluster-md-kmp-rt / dlm-kmp-rt / gfs2-kmp-rt / kernel-devel-rt / etc (SUSE-SU-2022:4617-1)

The remote SUSE Linux SLES15 / openSUSE 15 host has packages installed that are affected by multiple vulnerabilities as referenced in the SUSE-SU-2022:4617-1 advisory. The SUSE Linux Enterprise 15 SP4 RT kernel was updated to receive various security and bugfixes. The following security bugs were...

hw: cpu: AMD: RetBleed Arbitrary Speculative Code Execution with Return Instructions

A flaw was found in hw. Mis-trained branch predictions for return instructions may allow arbitrary speculative code execution under certain microarchitecture-dependent conditions...

hw: cpu: AMD: RetBleed Arbitrary Speculative Code Execution with Return Instructions

A flaw was found in hw. Mis-trained branch predictions for return instructions may allow arbitrary speculative code execution under certain microarchitecture-dependent conditions...

hw: cpu: AMD: RetBleed Arbitrary Speculative Code Execution with Return Instructions

A flaw was found in hw. Mis-trained branch predictions for return instructions may allow arbitrary speculative code execution under certain microarchitecture-dependent conditions...

hw: cpu: AMD: RetBleed Arbitrary Speculative Code Execution with Return Instructions

A flaw was found in hw. Mis-trained branch predictions for return instructions may allow arbitrary speculative code execution under certain microarchitecture-dependent conditions...