Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Large Language Models LLMs are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial suffixes are considered to be the current state-of-the-art...

Robustness Analysis against Adversarial Patch Attacks in Fully Unmanned Stores

The advent of convenient and efficient fully unmanned stores equipped with artificial intelligence-based automated checkout systems marks a new era in retail. However, these systems have inherent artificial intelligence security vulnerabilities, which are exploited via adversarial patch attacks,...

DP-TRAE: a Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

In the field of digital security, Reversible Adversarial Examples RAE combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural Networks DNNs. However, existing RAE techniques primarily focus...

POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models

Large language models LLMs have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite their impressive performance, LLMs are susceptible to hallucinations, which can lead to incorrect or misleading outputs...

CVE-2025-47447

Cross-Site Request Forgery CSRF vulnerability in Hossni Mubarak Cool Author Box hm-cool-author-box-widget allows Cross Site Request Forgery.This issue affects Cool Author Box: from n/a through = 3.0.0...

CVE-2025-47447

Cross-Site Request Forgery CSRF vulnerability in Hossni Mubarak Cool Author Box hm-cool-author-box-widget allows Cross Site Request Forgery.This issue affects Cool Author Box: from n/a through = 3.0.0...

CVE-2025-47447 WordPress Cool Author Box plugin <= 3.0.0 - Cross Site Request Forgery (CSRF) Vulnerability

Cross-Site Request Forgery CSRF vulnerability in Hossni Mubarak Cool Author Box hm-cool-author-box-widget allows Cross Site Request Forgery.This issue affects Cool Author Box: from n/a through = 3.0.0...

CVE-2025-47447

CVE-2025-47447 is a Cross-Site Request Forgery (CSRF) vulnerability in the WordPress plugin “Cool Author Box” (vulnerable through 3.0.0). The issue stems from CSRF protection gaps in Cool Author Box, enabling CSRF exploitation. Public sources (Patchstack, PT-Security) indicate affected versions u...

WordPress Cool Author Box plugin <= 3.0.0 - Cross Site Request Forgery (CSRF) Vulnerability

Cross Site Request Forgery CSRF Vulnerability discovered by Nabil Irawan in WordPress Plugin Cool Author Box versions = 3.0.0...

PT-2025-20083 · Unknown · Hossni Mubarak Cool Author Box

Name of the Vulnerable Software and Affected Versions: Hossni Mubarak Cool Author Box versions prior to 3.0.0 Description: The issue is a Cross-Site Request Forgery CSRF vulnerability, which allows for Cross Site Request Forgery. Recommendations: For versions prior to 3.0.0, update to version 3.0...

WordPress plugin Cool Author Box 跨站请求伪造漏洞

WordPress and WordPress plugin are both products of the WordPress Foundation.WordPress is a blogging platform developed in the PHP language. The platform supports setting up personal blog sites on servers with PHP and MySQL. WordPress plugin is an application plugin. A cross-site request forgery...

The vulnerability of the gf_hevc_read_sps_bs_internal function in the MP4Box module of the GPAC multimedia platform allows a hacker to execute arbitrary code.

The vulnerability of the gfhevcreadspsbsinternal function in the MP4Box module of the GPAC multimedia platform is related to integer overflow. Exploiting this vulnerability could allow an attacker to execute arbitrary code...

CVE-2025-2488

Improper Neutralization of Input During Web Page Generation XSS or 'Cross-site Scripting' vulnerability in Profelis Informatics SambaBox allows Cross-Site Scripting XSS. This issue affects SambaBox: before 5.1...

CVE-2025-2488

Improper Neutralization of Input During Web Page Generation XSS or 'Cross-site Scripting' vulnerability in Profelis Informatics SambaBox allows Cross-Site Scripting XSS.This issue affects SambaBox: before 5.1...

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...

Unlocking User-Oriented Pages: Intention-Driven Black-Box Scanner for Real-World Web Applications

Black-box scanners have played a significant role in detecting vulnerabilities for web applications. A key focus in current black-box scanning is increasing test coverage i.e., accessing more web pages. However, since many web applications are user-oriented, some deep pages can only be accessed...

The vulnerability of the ctts_box_write function in the isomedia/box_code_base.c file of the MP4Box packaging tool of the GPAC multimedia platform allows a hacker to cause a service failure.

The vulnerability of the cttsboxwrite function in the isomedia/boxcodebase.c file of the MP4Box packaging tool for the GPAC multimedia platform is related to the assignment of a null pointer. Exploiting this vulnerability could allow an attacker to cause a service failure...

SentinelOne Uncovers Chinese Espionage Campaign Targeting Its Infrastructure and Clients

Cybersecurity company SentinelOne has revealed that a China-nexus threat cluster dubbed PurpleHaze conducted reconnaissance attempts against its infrastructure and some of its high-value customers. "We first became aware of this threat cluster during a 2024 intrusion conducted against an...

AGATE: Stealthy Black-Box Watermarking for Multimodal Model Copyright Protection

Recent advancement in large-scale Artificial Intelligence AI models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution OoD data as backdoor watermarks and retrain the original model for...

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs

The challenge of ensuring Large Language Models LLMs align with societal standards is of increasing interest, as these models are still prone to adversarial jailbreaks that bypass their safety mechanisms. Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against su...