FlowPure: Continuous Normalizing Flows for Adversarial Purification

Despite significant advancements in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has emerged as a promising defense strategy. To achieve...

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...

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...

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...

Quantifying Source Speaker Leakage in One-To-One Voice Conversion

Using a multi-accented corpus of parallel utterances for use with commercial speech devices, we present a case study to show that it is possible to quantify a degree of confidence about a source speaker's identity in the case of one-to-one voice conversion. Following voice conversion using a...

Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails

Large Language Models LLMs guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection and jailbreak detection systems via traditional character...

Fake Snow White Movie Torrent Infects Devices with Malware

Disney’s latest Snow White movie, with a 1.6/10 IMDb rating, isn’t just the biggest flop the company has…...

jst-southafrica.com Cross Site Scripting vulnerability OBB-4040076

Following the coordinated and responsible vulnerability disclosure guidelines of the ISO 29147 standard, Open Bug Bounty has: a. verified the vulnerability and confirmed its existence; b. notified the website operator about its existence. Technical details of the vulnerability are currently hidde...

Using Starlink Wi-Fi in the White House Is a Slippery Slope for US Federal IT

The ad hoc addition to the otherwise tightly controlled White House information environment could create blind spots and security exposures while setting potentially dangerous precedent...

live.tdpu.uz Cross Site Scripting vulnerability OBB-4033959

Following the coordinated and responsible vulnerability disclosure guidelines of the ISO 29147 standard, Open Bug Bounty has: a. verified the vulnerability and confirmed its existence; b. notified the website operator about its existence. Technical details of the vulnerability are currently hidde...

crocurry.com Cross Site Scripting vulnerability OBB-4033227

Following the coordinated and responsible vulnerability disclosure guidelines of the ISO 29147 standard, Open Bug Bounty has: a. verified the vulnerability and confirmed its existence; b. notified the website operator about its existence. Technical details of the vulnerability are currently hidde...

CVE-2024-57176

An issue in the shiroFilter function of White-Jotter project v0.2.2 allows attackers to execute a directory traversal and access sensitive endpoints via a crafted URL...

CVE-2024-57176

An issue in the shiroFilter function of White-Jotter project v0.2.2 allows attackers to execute a directory traversal and access sensitive endpoints via a crafted URL...

White-Jotter 安全漏洞

White-Jotter is a front-end and back-end separation project developed by Antabot individual developer using Vue+Spring Boot, with a full set of development tutorials. White-Jotter has a security vulnerability that stems from an issue in the shiroFilter function. An attacker exploiting this...

CVE-2024-57176

CVE-2024-57176 affects White-Jotter v0.2.2. Multiple sources describe a vulnerability in the shiroFilter function that allows directory traversal, enabling an attacker to access sensitive endpoints via a crafted URL. The issue is documented across CVE registries and vendor advisories with consist...

PT-2025-7447 · Unknown · White-Jotter

Name of the Vulnerable Software and Affected Versions: White-Jotter version 0.2.2 Description: An issue in the shiroFilter function allows attackers to execute a directory traversal and access sensitive endpoints via a crafted URL. Recommendations: Update to a newer version of White-Jotter that...

CVE-2024-57176

An issue in the shiroFilter function of White-Jotter project v0.2.2 allows attackers to execute a directory traversal and access sensitive endpoints via a crafted URL...

CVE-2024-57176

An issue in the shiroFilter function of White-Jotter project v0.2.2 allows attackers to execute a directory traversal and access sensitive endpoints via a crafted URL...

CVE-2024-57176

An issue in the shiroFilter function of White-Jotter project v0.2.2 allows attackers to execute a directory traversal and access sensitive endpoints via a crafted URL...

CVE-2025-24541

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in dinamiko DK White Label dk-white-label allows Reflected XSS.This issue affects DK White Label: from n/a through = 1.0...