CVE-2025-23313

NVIDIA NeMo Framework for all platforms contains a vulnerability in the NLP component, where malicious data created by an attacker could cause a code injection issue. A successful exploit of this vulnerability might lead to code execution, escalation of privileges, information disclosure, and dat...

CVE-2025-23313

Summary (CVE-2025-23313) : NVIDIA NeMo Framework (NLP component) across platforms is described as vulnerable to code injection via malicious data. The underlying root cause is not detailed in the provided documents, but the consequence could include code execution, privilege escalation, informati...

PT-2025-34804 · Nvidia · Nvidia Nemo Framework

Name of the Vulnerable Software and Affected Versions: NVIDIA NeMo Framework affected versions not specified Description: The NVIDIA NeMo Framework contains an issue in the NLP component that could allow an attacker to inject code through maliciously crafted data. A successful exploit may lead to...

NVIDIA Nemo Framework 代码注入漏洞

NVIDIA Nemo Framework is a framework for building and deploying generative AI models from NVIDIA. The NVIDIA Nemo Framework suffers from a code injection vulnerability that stems from malicious data in the NLP component that could lead to code injection, which in turn could lead to code execution...

DINA: a Dual Defense Framework against Internal Noise and External Attacks in Natural Language Processing

As large language models LLMs and generative AI become increasingly integrated into customer service and moderation applications, adversarial threats emerge from both external manipulations and internal label corruption. In this work, we identify and systematically address these dual adversarial...

Automated Attack Testflow Extraction from Cyber Threat Report Using BERT for Contextual Analysis

In the ever-evolving landscape of cybersecurity, the rapid identification and mitigation of Advanced Persistent Threats APTs is crucial. Security practitioners rely on detailed threat reports to understand the tactics, techniques, and procedures TTPs employed by attackers. However, manually...

BackFed: an Efficient and Standardized Benchmark Suite for Backdoor Attacks in Federated Learning

Federated Learning FL systems are vulnerable to backdoor attacks, where adversaries train their local models on poisoned data and submit poisoned model updates to compromise the global model. Despite numerous proposed attacks and defenses, divergent experimental settings, implementation errors, a...

Enhancing Phishing Detection in Financial Systems through NLP

The threat of phishing attacks in financial systems is continuously growing. Therefore, protecting sensitive information from unauthorized access is paramount. This paper discusses the critical need for robust email phishing detection. Several existing methods, including blacklists and whitelists...

Human-Centred AI in FinTech: Developing a User Experience (UX) Research Point of View (PoV) Playbook

Advancements in Artificial Intelligence AI have significantly transformed the financial industry, enabling the development of more personalized and adaptable financial products and services. This research paper explores various instances where Human-Centred AI HCAI has facilitated these...

ModelForge: Using GenAI to Improve the Development of Security Protocols

Formal methods can be used for verifying security protocols, but their adoption can be hindered by the complexity of translating natural language protocol specifications into formal representations. In this paper, we introduce ModelForge, a novel tool that automates the translation of protocol...

CVE-2024-48746

An issue in Lens Visual integration with Power BI v.4.0.0.3 allows a remote attacker to execute arbitrary code via the Natural language processing component...

Securing the Future of IVR: AI-Driven Innovation with Agile Security, Data Regulation, and Ethical AI Integration

The rapid digitalization of communication systems has elevated Interactive Voice Response IVR technologies to become critical interfaces for customer engagement. With Artificial Intelligence AI now driving these platforms, ensuring secure, compliant, and ethically designed development practices i...

Microsoft Azure Bot Framework SDK 授权问题漏洞

The Microsoft Azure Bot Framework SDK is a development framework for building, testing, and deploying enterprise-grade conversational AI bots with support for multi-channel integration and natural language processing from Microsoft USA. An authorization issue vulnerability exists in the Microsoft...

ReGraph: a Tool for Binary Similarity Identification

Binary Code Similarity Detection BCSD is not only essential for security tasks such as vulnerability identification but also for code copying detection, yet it remains challenging due to binary stripping and diverse compilation environments. Existing methods tend to adopt increasingly complex...

Bitcoin'S Edge: Embedded Sentiment in Blockchain Transactional Data

Cryptocurrency blockchains, beyond their primary role as distributed payment systems, are increasingly used to store and share arbitrary content, such as text messages and files. Although often non-financial, this hidden content can impact price movements by conveying private information, shaping...

CVE-2024-48746

An issue in Lens Visual integration with Power BI v.4.0.0.3 allows a remote attacker to execute arbitrary code via the Natural language processing component...

PT-2024-33199 · Microsoft · Power Bi

Name of the Vulnerable Software and Affected Versions: Power BI version 4.0.0.3 Description: An issue in Lens Visual integration with Power BI allows a remote attacker to execute arbitrary code via the Natural language processing component. Recommendations: For Power BI version 4.0.0.3, consider...

CVE-2024-48746

CVE-2024-48746 affects Lens Visual integration with Power BI v4.0.0.3. The issue allows a remote attacker to execute arbitrary code via the Natural Language Processing component. The vulnerability is described across multiple sources (NVD/Red Hat/CNNVD) with a high impact and CVSS v3.1 base score...

CVE-2024-48746

An issue in Lens Visual integration with Power BI v.4.0.0.3 allows a remote attacker to execute arbitrary code via the Natural language processing component...

Lens Visual integration with Power BI 安全漏洞

Lens Visual integration with Power BI is a program from Lens Visual, Inc. Enhances Power BI dashboards with OpenAI and ChatGPT. A security vulnerability exists in Lens Visual integration with Power BI version v.4.0.0.3, which originates from a vulnerability that could allow a remote attacker to...