One Trigger Token Is Enough: a Defense Strategy for Balancing Safety and Usability in Large Language Models

Large Language Models LLMs have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they remain vulnerable to jailbreak attacks, which manipulate the models into generating harmful responses despite safety...

Revealing Weaknesses in Text Watermarking through Self-Information Rewrite Attacks

Text watermarking aims to subtly embed statistical signals into text by controlling the Large Language Model LLM's sampling process, enabling watermark detectors to verify that the output was generated by the specified model. The robustness of these watermarking algorithms has become a key factor...

RuleGenie: SIEM Detection Rule Set Optimization

SIEM systems serve as a critical hub, employing rule-based logic to detect and respond to threats. Redundant or overlapping rules in SIEM systems lead to excessive false alerts, degrading analyst performance due to alert fatigue, and increase computational overhead and response latency for actual...

OESA-2025-1493 qt6-qtbase security update

Qt is a software toolkit for developing applications. Security Fixes: encodeText in QDom in Qt before 6.8.0 has a complex algorithm involving XML string copy and inline replacement of parts of a string with relocation of later data.CVE-2025-30348...

CVE-2025-4376

CVE-2025-4376 : Sparx Systems Pro Cloud Server’s WebEA model search field is affected by an improper input validation causing Cross-Site Scripting (XSS). Impact applies to Pro Cloud Server versions earlier than 6.0.165. Remediation: upgrade to version 6.0.165 or later. Exploitation details are no...

CVE-2025-4376 Cross-Site Scripting vulnerability in Model Search in Pro Cloud Server's WebEA

Improper Input Validation vulnerability in Sparx Systems Pro Cloud Server's WebEA model search field allows Cross-Site Scripting XSS. This issue affects Pro Cloud Server: earlier than 6.0.165...

Sparx Systems Pro Cloud Server 安全漏洞

Sparx Systems Pro Cloud Server is an enterprise-class model collaboration platform from Sparx Systems Australia that supports cloud sharing and version control of EA Enterprise Architect models. A security vulnerability exists in Sparx Systems Pro Cloud Server versions prior to 6.0.165, which ste...

Sparx Systems Pro Cloud Server 安全漏洞

Sparx Systems Pro Cloud Server is an enterprise-class model collaboration platform from Sparx Systems Australia that supports cloud sharing and version control of EA Enterprise Architect models. A security vulnerability exists in Sparx Systems Pro Cloud Server versions prior to 6.0.165, which ste...

Security Steerability Is All You Need

The adoption of Generative AI GenAI in various applications inevitably comes with expanding the attack surface, combining new security threats along with the traditional ones. Consequently, numerous research and industrial initiatives aim to mitigate these security threats in GenAI by developing...

LATENT: LLM-Augmented Trojan Insertion and Evaluation Framework for Analog Netlist Topologies

Analog and mixed-signal A/MS integrated circuits ICs are integral to safety-critical applications. However, the globalization and outsourcing of A/MS ICs to untrusted third-party foundries expose them to security threats, particularly analog Trojans. Unlike digital Trojans which have been...

Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense Via Model Pruning

Recent studies have shown that sponge attacks can significantly increase the energy consumption and inference latency of deep neural networks DNNs. However, prior work has focused primarily on computer vision and natural language processing tasks, overlooking the growing use of lightweight AI...

ATEN LCD KVM over IP Switch CL5708IM 安全漏洞

ATEN LCD KVM over IP Switch CL5708IM is an 8-port IP KVM switch with LCD screen from China's ATEN Automation ATEN that supports remote BIOS-level device management. A security vulnerability exists in the ATEN LCD KVM over IP Switch CL5708IM, which originates from a stack buffer overflow and could...

CVE-2024-45581

Memory corruption while sound model registration for voice activation with audio kernel driver...

Large Language Model-Driven Security Assistant for Internet of Things Via Chain-Of-Thought

The rapid development of Internet of Things IoT technology has transformed people's way of life and has a profound impact on both production and daily activities. However, with the rapid advancement of IoT technology, the security of IoT devices has become an unavoidable issue in both research an...

An Agent-Based Modeling Approach to Free-Text Keyboard Dynamics for Continuous Authentication

Continuous authentication systems leveraging free-text keyboard dynamics offer a promising additional layer of security in a multifactor authentication setup that can be used in a transparent way with no impact on user experience. This study investigates the efficacy of behavioral biometrics by...

Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security

Federated learning FL enables collaborative model training while preserving user data privacy by keeping data local. Despite these advantages, FL remains vulnerable to privacy attacks on user updates and model parameters during training and deployment. Secure aggregation protocols have been...

TOTOLINK A950RG 安全漏洞

The TOTOLINK A950RG is an ultra-generation Giga wireless router from China's Gion Electronics TOTOLINK. The TOTOLINK A950RG suffers from a buffer overflow vulnerability that originates from the failure of the setNoticeCfg interface NoticeUrl parameter in /lib/cstemodules/system.so to correctly...

MTL-UE: Learning to Learn Nothing for Multi-Task Learning

Most existing unlearnable strategies focus on preventing unauthorized users from training single-task learning STL models with personal data. Nevertheless, the paradigm has recently shifted towards multi-task data and multi-task learning MTL, targeting generalist and foundation models that can...

Privacy-Preserving Transformers: SwiftKey'S Differential Privacy Implementation

In this paper we train a transformer using differential privacy DP for language modeling in SwiftKey. We run multiple experiments to balance the trade-off between the model size, run-time speed and accuracy. We show that we get small and consistent gains in the next-word-prediction and accuracy...

CVE-2025-43851

Retrieval-based-Voice-Conversion-WebUI is a voice changing framework based on VITS. Versions 2.2.231006 and prior are vulnerable to unsafe deserialization. The modelchoose variable takes user input e.g. a path to a model and passes it to the uvr function in vr.py. In uvr , a new instance of...