Lucene search
+L

4008 matches found

The Hacker News
The Hacker News
added 2025/05/03 7:06 a.m.54 views

U.S. Charges Yemeni Hacker Behind Black Kingdom Ransomware Targeting 1,500 Systems

The U.S. Department of Justice DoJ on Thursday announced charges against a 36-year-old Yemeni national for allegedly deploying the Black Kingdom ransomware against global targets, including businesses, schools, and hospitals in the United States. Rami Khaled Ahmed of Sana'a, Yemen, has been charg...

10CVSS10AI score0.99999EPSS
SaveExploits22
Packet Storm News
Packet Storm News
added 2025/05/01 12:00 a.m.10 views

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...

7.6AI score
SaveExploits0
The Hacker News
The Hacker News
added 2025/04/30 10:24 a.m.15 views

Customer Account Takeovers: The Multi-Billion Dollar Problem You Don't Know About

Everyone has cybersecurity stories involving family members. Here's a relatively common one. The conversation usually goes something like this: "The strangest thing happened to my streaming account. I got locked out of my account, so I had to change my password. When I logged back in, all my show...

7.6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/04/30 12:00 a.m.13 views

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...

7.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/04/28 12:00 a.m.27 views

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...

6.9AI score
SaveExploits0
Citrix
Citrix
added 2025/04/28 12:00 a.m.13 views

Black area's when launching Horizon app on VDA 2402 CU1

After upgrading our VDA to 2402 cu1 we are presented with black artifacts on launch of Horizon app...

7.1AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/04/26 12:00 a.m.11 views

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...

7.6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/04/20 12:00 a.m.15 views

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-Box Large Language Models

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to generate poisoned texts and improve the stealthiness,...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/04/18 12:00 a.m.9 views

Q-FAKER: Query-Free Hard Black-Box Attack Via Controlled Generation

Many adversarial attack approaches are proposed to verify the vulnerability of language models. However, they require numerous queries and the information on the target model. Even black-box attack methods also require the target model's output information. They are not applicable in real-world...

6.7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/04/16 12:00 a.m.9 views

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...

7.4AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/04/15 12:00 a.m.8 views

Token-Level Constraint Boundary Search for Jailbreaking Text-To-Image Models

Recent advancements in Text-to-Image T2I generation have significantly enhanced the realism and creativity of generated images. However, such powerful generative capabilities pose risks related to the production of inappropriate or harmful content. Existing defense mechanisms, including prompt...

7AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
added 2025/04/14 10:00 a.m.6 views

Black Basta: The Fallen Ransomware Gang That Lives On

After a series of setbacks, the notorious Black Basta ransomware gang went underground. Researchers are bracing for its probable return in a new form...

7.3AI score
SaveExploits0
Malwarebytes
Malwarebytes
added 2025/04/08 2:34 p.m.15 views

Google AI taken for a ride by April Fools’ Day joke

Cwmbran in Wales, a town with a population of just under 50,000, holds the Guinness World Record for the most roundabouts—at least according to Google AI Overviews. Except that's not actually true… Ben Black has been publishing lighthearted fake stories on April Fools’ Day for his community news...

7.1AI score
SaveExploits0
RedhatCVE
RedhatCVE
added 2025/04/03 3:45 p.m.17 views

CVE-2025-31869

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in Modernaweb Studio Black Widgets For Elementor black-widgets allows Stored XSS.This issue affects Black Widgets For Elementor: from n/a through = 1.3.9...

6.5CVSS7.2AI score0.00258EPSS
SaveExploits0References1
NVD
NVD
added 2025/04/01 3:16 p.m.26 views

CVE-2025-31869

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in Modernaweb Studio Black Widgets For Elementor black-widgets allows Stored XSS.This issue affects Black Widgets For Elementor: from n/a through = 1.3.9...

6.5CVSS0.00258EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
added 2025/04/01 2:52 p.m.8 views

CVE-2025-31869 WordPress Black Widgets For Elementor plugin <= 1.3.9 - Cross Site Scripting (XSS) vulnerability

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in Modernaweb Studio Black Widgets For Elementor allows Stored XSS. This issue affects Black Widgets For Elementor: from n/a through 1.3.9...

6.5CVSS6.9AI score0.00258EPSS
SaveExploits0References1
Cvelist
Cvelist
added 2025/04/01 2:52 p.m.36 views

CVE-2025-31869 WordPress Black Widgets For Elementor plugin <= 1.3.9 - Cross Site Scripting (XSS) vulnerability

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in Modernaweb Studio Black Widgets For Elementor black-widgets allows Stored XSS.This issue affects Black Widgets For Elementor: from n/a through = 1.3.9...

6.5CVSS0.00258EPSS
SaveExploits0References1
Positive Technologies
Positive Technologies
added 2025/04/01 12:00 a.m.9 views

PT-2025-14246 · Unknown · Black Widgets For Elementor

Name of the Vulnerable Software and Affected Versions: Black Widgets For Elementor versions 1.3.9 and earlier Description: The issue is related to Improper Neutralization of Input During Web Page Generation, also known as Cross-site Scripting, which allows Stored XSS. This means that an attacker...

6.5CVSS6.8AI score0.00258EPSS
SaveExploits0References4
CNNVD
CNNVD
added 2025/04/01 12:00 a.m.10 views

WordPress plugin Black Widgets For Elementor 跨站脚本漏洞

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

6.5CVSS6.4AI score0.00258EPSS
SaveExploits0References2
CNNVD
CNNVD
added 2025/03/31 12:00 a.m.8 views

Black Duck Coverity 跨站脚本漏洞

Black Duck Coverity is a comprehensive static code analysis and software security tool from Black Duck, Inc. It is used to find and fix vulnerabilities, defects and security risks in software. A cross-site scripting vulnerability exists in versions prior to Black Duck Coverity 2024.9.0, which...

8.5CVSS5.6AI score0.00368EPSS
SaveExploits0References1
Rows per page
Query Builder