WordPress plugin The Fashion - Model Agency One Page Beauty Theme Code Issue Vulnerability

WordPress and WordPress plugin are both products of the WordPress Foundation.WordPress is a blogging platform developed using the PHP language. The platform supports setting up personal blog sites on servers with PHP and MySQL.WordPress plugin is an application plugin. A code issue vulnerability...

Konica Minolta bizhub 代码注入漏洞

The Konica Minolta bizhub is a multifunction printer from the Japanese company Konica Minolta. A code injection vulnerability exists in Konica Minolta bizhub 20250202 and earlier versions, which stems from cross-site scripting due to incorrect manipulation of the parameter Model Name...

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models

Large Language Models LLMs memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information PII, which should not be stored and, consequently, not leaked. In this paper, we introduce Private Memorization Editing PME, an approach for preventing private...

Securing Unbounded Differential Privacy against Timing Attacks

Recent works have started to theoretically investigate how we can protect differentially private programs against timing attacks, by making the joint distribution the output and the runtime differentially private JOT-DP. However, the existing approaches to JOT-DP have some limitations, particular...

PT-2025-24477 · Unknown · The Fashion - Model Agency One Page Beauty Theme

Name of the Vulnerable Software and Affected Versions: The Fashion - Model Agency One Page Beauty Theme versions 1.4.4 and earlier Description: The issue is related to Deserialization of Untrusted Data, which allows Object Injection. Recommendations: For versions 1.4.4 and earlier, update to a...

Evaluating Explainable AI for Deep Learning-Based Network Intrusion Detection System Alert Classification

A Network Intrusion Detection System NIDS monitors networks for cyber attacks and other unwanted activities. However, NIDS solutions often generate an overwhelming number of alerts daily, making it challenging for analysts to prioritize high-priority threats. While deep learning models promise to...

GradEscape: a Gradient-Based Evader against AI-Generated Text Detectors

In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text AIGT detectors. GradEscape overcomes the undifferentiable computation problem, caused by the discrete nature of text, by introducing a novel approach to construct weighted embeddings for t...

SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows

Large language models LLMs have seen widespread success in code generation tasks for different scenarios, both everyday and professional. However current LLMs, despite producing functional code, do not prioritize security and may generate code with exploitable vulnerabilities. In this work, we...

D2R: Dual Regularization Loss with Collaborative Adversarial Generation for Model Robustness

The robustness of Deep Neural Network models is crucial for defending models against adversarial attacks. Recent defense methods have employed collaborative learning frameworks to enhance model robustness. Two key limitations of existing methods are i insufficient guidance of the target model via...

MARVEL: Multi-Agent RTL Vulnerability Extraction Using Large Language Models

Hardware security verification is a challenging and time-consuming task. For this purpose, design engineers may utilize tools such as formal verification, linters, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being inspected. Large Languag...

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

The remarkable success of Large Language Models LLMs has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both...

Enhanced Consistency Bi-Directional GAN(CBiGAN) for Malware Anomaly Detection

Static analysis, a cornerstone technique in cybersecurity, offers a noninvasive method for detecting malware by analyzing dormant software without executing potentially harmful code. However, traditional static analysis often relies on biased or outdated datasets, leading to gaps in detection...

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment

Safely aligning large language models LLMs often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on complex iterative prompting or auxiliary models. To address...

Ikonomos Skyvern 安全漏洞

Ikonomos Skyvern is a software from Ikonomos, Inc. in the United States. A security vulnerability exists in Ikonomos Skyvern 0.1.85 and earlier versions, which originates from a Jinja runtime leak in sdk/workflow/models/block.py...

Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance

Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' susceptibility to diverse jailbreak attacks. Concurrently, inference scaling has significantly advanced LLM reasoning...

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation RAG systems enhance Large Language Models LLMs by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on...

Stealix: Model Stealing Via Prompt Evolution

Model stealing poses a significant security risk in machine learning by enabling attackers to replicate a black-box model without access to its training data, thus jeopardizing intellectual property and exposing sensitive information. Recent methods that use pre-trained diffusion models for data...

SATversary: Adversarial Attacks on Satellite Fingerprinting

As satellite systems become increasingly vulnerable to physical layer attacks via SDRs, novel countermeasures are being developed to protect critical systems, particularly those lacking cryptographic protection, or those which cannot be upgraded to support modern cryptography. Among these is...

Demystifying Myth Stealer: A Rust Based InfoStealer

Demystifying Myth Stealer: A Rust Based InfoStealer By Niranjan Hegde, Vasantha Lakshmanan Ambasankar and Adarsh S · June 5, 2025 Introduction During regular proactive threat hunting, the Trellix Advanced Research Center identified a fully undetected infostealer malware sample written in Rust. Up...

Incentivizing Collaborative Breach Detection

Decoy passwords, or "honeywords," alert a site to its breach if they are ever entered in a login attempt on that site. However, an attacker can identify a user-chosen password from among the decoys, without risk of alerting the site to its breach, by performing credential stuffing, i.e., entering...