CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

Model compression is crucial for minimizing memory storage and accelerating inference in deep learning DL models, including recent foundation models like large language models LLMs. Users can access different compressed model versions according to their resources and budget. However, while existi...

AUTOPSY: a Framework for Tackling Privacy Challenges in the Automotive Industry

With the General Data Protection Regulation GDPR in place, all domains have to ensure compliance with privacy legislation. However, compliance does not necessarily result in a privacy-friendly system as for example getting users' consent to process their data does not improve the...

CVE-2025-53832

Lara Translate MCP Server is a Model Context Protocol MCP Server for Lara Translate API. Versions 0.0.11 and below contain a command injection vulnerability which exists in the @translated/lara-mcp MCP Server. The vulnerability is caused by the unsanitized use of input parameters within a call to...

CVE-2025-7222

Luxion KeyShot 3DM File Parsing Out-Of-Bounds Write Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Luxion KeyShot. User interaction is required to exploit this vulnerability in that the target must visit a...

Chaindesk Cross Site Scripting

Chaindesk, a web application for constructing AI Agents, is vulnerable to a persistent cross site scripting vulnerability in its agent chat component. An attacker can achieve arbitrary client-side script execution by crafting an AI agent whose system prompt instructs the underlying Large Language...

FaultLine: Automated Proof-Of-Vulnerability Generation Using LLM Agents

Despite the critical threat posed by software security vulnerabilities, reports are often incomplete, lacking the proof-of-vulnerability PoV tests needed to validate fixes and prevent regressions. These tests are crucial not only for ensuring patches work, but also for helping developers understa...

SynthCTI: LLM-Driven Synthetic CTI Generation to Enhance MITRE Technique Mapping

Cyber Threat Intelligence CTI mining involves extracting structured insights from unstructured threat data, enabling organizations to understand and respond to evolving adversarial behavior. A key task in CTI mining is mapping threat descriptions to MITRE ATT&CK techniques. However, this process...

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems

Large Language Models LLMs deployed in enterprise settings e.g., as Microsoft 365 Copilot face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually extract confidential data. In this paper, we present a...

Scaling Decentralized Learning with FLock

Fine-tuning the large language models LLMs are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized schemes. While the typical standard federated learning FL supports data privacy, the central server requirement creates a...

Remote Code Execution (RCE)

github.com/juju/juju is vulnerable to Remote Code Execution RCE. The vulnerability is due to insufficient authorization checks caused by allowing any authenticated controller user to upload arbitrary agent binaries to any model or the controller without verifying model membership or permissions...

SUSE-SU-2025:02366-1 Security update for docker

This update for docker fixes the following issues: Update to Docker 28.2.2-ce bsc1243833, bsc1242114: - CVE-2025-22872: golang.org/x/net/html: incorrectly interpreted tags can cause content to be placed wrong scope during DOM construction bsc1241830. Other bugfixes: - Always clear SUSEConnect sus...

CERT-UA Discovers LAMEHUG Malware Linked to APT28, Using LLM for Phishing Campaign

The Computer Emergency Response Team of Ukraine CERT-UA has disclosed details of a phishing campaign that's designed to deliver a malware codenamed LAMEHUG. "An obvious feature of LAMEHUG is the use of LLM large language model, used to generate commands based on their textual representation...

XWiki 16.10.0-rc-1 < 16.10.4, 17.0.0-rc-1 < 17.1.0 RCE Vulnerability (GHSA-rhfv-688c-p6hp)

Xwiki is prone to a remote code execution RCE vulnerability. SPDX-FileCopyrightText: 2025 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 CPE = "cpe:/a:xwiki:xwiki";...

Breaking the Illusion of Security Via Interpretation: Interpretable Vision Transformer Systems under Attack

Vision transformer ViT models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains such as medical applications, autonomous vehicles, drones, and robotics. However, successful attacks on these systems ca...

Perplexity AI Web Application 安全漏洞

Perplexity AI Web Application is a big data search engine application utilizing a big language model from Perplexity, Inc. in the United States. A security vulnerability exists in Perplexity AI Web Application GPT-4 version 2.51.0, which stems from mishandling of the token component and could lea...

CVE-2025-49838

GPT-SoVITS-WebUI is a voice conversion and text-to-speech webUI. In versions 20250228v3 and prior, there is an unsafe deserialization vulnerability in vr.py AudioPreDeEcho. The modelchoose variable takes user input e.g. a path to a model and passes it to the uvr function. In uvr, a new instance o...

CVE-2025-49839

GPT-SoVITS-WebUI is a voice conversion and text-to-speech webUI. In versions 20250228v3 and prior, there is an unsafe deserialization vulnerability in bsroformer.py. The modelchoose variable takes user input e.g. a path to a model and passes it to the uvr function. In uvr, a new instance of...

CVE-2025-49837

GPT-SoVITS-WebUI is a voice conversion and text-to-speech webUI. In versions 20250228v3 and prior, there is an unsafe deserialization vulnerability in vr.py AudioPre. The modelchoose variable takes user input e.g. a path to a model and passes it to the uvr function. In uvr, a new instance of...

Expanding ML-Documentation Standards for Better Security

This article presents the current state of ML-security and of the documentation of ML-based systems, models and datasets in research and practice based on an extensive review of the existing literature. It shows a generally low awareness of security aspects among ML-practitioners and organization...

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques

Large Language Models LLMs are transforming cybersecurity by enabling intelligent, adaptive, and automated approaches to threat detection, vulnerability assessment, and incident response. With their advanced language understanding and contextual reasoning, LLMs surpass traditional methods in...