Horner Automation Cscape

RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker to disclose information and execute arbitrary code. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of exploitation of this vulnerability, such as: Minimize network...

Defending against Indirect Prompt Injection by Instruction Detection

The integration of Large Language Models LLMs with external sources is becoming increasingly common, with Retrieval-Augmented Generation RAG being a prominent example. However, this integration introduces vulnerabilities of Indirect Prompt Injection IPI attacks, where hidden instructions embedded...

CVE-2025-36525 BIG-IP APM PingAccess Virtual Server Vulnerability

When a BIG-IP APM virtual server is configured to use a PingAccess profile, undisclosed requests can cause TMM to terminate. Note: Software versions which have reached End of Technical Support EoTS are not evaluated...

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models

Large language models LLMs trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose OBLIVIATE, a robust unlearning framework that removes targeted data while preserving model utility. The framework follows a structured process: extractin...

Safeguard-By-Development: a Privacy-Enhanced Development Paradigm for Multi-Agent Collaboration Systems

Multi-agent collaboration systems MACS, powered by large language models LLMs, solve complex problems efficiently by leveraging each agent's specialization and communication between agents. However, the inherent exchange of information between agents and their interaction with external...

Optigo Networks ONS NC600

RISK EVALUATION Successful exploitation of this vulnerability could allow an attacker to establish an authenticated connection with the hard-coded credentials and perform OS command executions. 2. RECOMMENDED PRACTICES CISA recommends users take defensive measures to minimize the risk of...

Towards a Standardized Methodology and Dataset for Evaluating LLM-Based Digital Forensic Timeline Analysis

Large language models LLMs have seen widespread adoption in many domains including digital forensics. While prior research has largely centered on case studies and examples demonstrating how LLMs can assist forensic investigations, deeper explorations remain limited, i.e., a standardized approach...

Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports Using Large Language Models

This work evaluates the performance of Cyber Threat Intelligence CTI extraction methods in identifying attack techniques from threat reports available on the web using the MITRE ATT&CK framework. We analyse four configurations utilising state-of-the-art tools, including the Threat Report ATT&CK...

PQS-BFL: a Post-Quantum Secure Blockchain-Based Federated Learning Framework

Federated Learning FL enables collaborative model training while preserving data privacy, but its classical cryptographic underpinnings are vulnerable to quantum attacks. This vulnerability is particularly critical in sensitive domains like healthcare. This paper introduces PQS-BFL Post-Quantum...

A False Sense of Privacy: Evaluating Textual Data Sanitization beyond Surface-Level Privacy Leakage

Whitepaper called A False Sense Of Privacy: Evaluating Textual Data Sanitization Beyond Surface-Level Privacy Leakage...

LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures

As large language models LLMs continue to evolve, it is critical to assess the security threats and vulnerabilities that may arise both during their training phase and after models have been deployed. This survey seeks to define and categorize the various attacks targeting LLMs, distinguishing...

OPA server Data API HTTP path injection of Rego

Impact When run as a server, OPA exposes an HTTP Data API for reading and writing documents. Requesting a virtual document through the Data API entails policy evaluation, where a Rego query containing a single data document reference is constructed from the requested path. This query is then used...

CVE-2022-49855 net: wwan: iosm: fix memory leak in ipc_pcie_read_bios_cfg

In the Linux kernel, the following vulnerability has been resolved: net: wwan: iosm: fix memory leak in ipcpciereadbioscfg ipcpciereadbioscfg is using the acpievaluatedsm to obtain the wwan power state configuration from BIOS but is not freeing the acpiobject. The acpievaluatedsm returned...

KUNBUS GmbH Revolution Pi (Update A)

RISK EVALUATION Successful exploitation of these vulnerabilities could allow attackers to bypass authentication, gain unauthorized access to critical functions, and execute malicious server-side includes SSI within a web page. 2. RECOMMENDED PRACTICES CISA recommends users take defensive...

Attack and Defense Techniques in Large Language Models: a Survey and New Perspectives

Large Language Models LLMs have become central to numerous natural language processing tasks, but their vulnerabilities present significant security and ethical challenges. This systematic survey explores the evolving landscape of attack and defense techniques in LLMs. We classify attacks into...

Elastic Elasticsearch 安全漏洞

Elastic Elasticsearch is a search engine based on the Lucene library from the Dutch company Elastic. A security vulnerability exists in Elastic Elasticsearch that stems from uncontrolled resource consumption when evaluating specially crafted search templates, which could lead to a denial of servi...

Can Differentially Private Fine-Tuning LLMs Protect against Privacy Attacks?

Fine-tuning large language models LLMs has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and exposed. Although differential privacy DP offers strong...

OET: Optimization-Based Prompt Injection Evaluation Toolkit

Large Language Models LLMs have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains. However, their susceptibility to prompt injection attacks poses significant security risks, as adversarial inputs can...

SoK: Enhancing Privacy-Preserving Software Development from a Developers' Perspective

In software development, privacy preservation has become essential with the rise of privacy concerns and regulations such as GDPR and CCPA. While several tools, guidelines, methods, methodologies, and frameworks have been proposed to support developers embedding privacy into software applications...

The Hidden Risks of LLM-Generated Web Application Code: a Security-Centric Evaluation of Code Generation Capabilities in Large Language Models

The rapid advancement of Large Language Models LLMs has enhanced software development processes, minimizing the time and effort required for coding and enhancing developer productivity. However, despite their potential benefits, code generated by LLMs has been shown to generate insecure code in...