New Best Practices Guide for Securing AI Data Released

Today, CISA, the National Security Agency, the Federal Bureau of Investigation, and international partners released a joint Cybersecurity Information Sheet on AI Data Security: Best Practices for Securing Data Used to Train & Operate AI Systems. This information sheet highlights the critical role...

CVE-2019-14261

An issue was discovered on ABUS Secvest FUAA50000 3.01.01 devices. Due to an insufficient implementation of jamming detection, an attacker is able to suppress correctly received RF messages sent between wireless peripheral components, e.g., wireless detectors or remote controls, and the ABUS...

CVE-2019-19547

Symantec Endpoint Detection and Response SEDR, prior to 4.3.0, may be susceptible to a cross site scripting XSS issue. XSS is a type of issue that can enable attackers to inject client-side scripts into web pages viewed by other users. An XSS vulnerability may be used by attackers to potentially...

CVE-2019-6672

On BIG-IP AFM 15.0.0-15.0.1, 14.0.0-14.1.2, and 13.1.0-13.1.3.1, when bad-actor detection is configured on a wildcard virtual server on platforms with hardware-based sPVA, the performance of the BIG-IP AFM system is degraded...

CVE-2019-6188

The BIOS tamper detection mechanism was not triggered in Lenovo ThinkPad T460p, BIOS versions up to R07ET90W, and T470p, BIOS versions up to R0FET50W, which may allow for unauthorized access...

CVE-2019-5360

A remote code execution vulnerability was identified in HPE Intelligent Management Center IMC PLAT earlier than version 7.3 E0506P09...

CVE-2016-3983

McAfee Advanced Threat Defense ATD before 3.4.8.178 might allow remote attackers to bypass malware detection by leveraging information about the parent process...

CVE-2012-1438

The Microsoft Office file parser in Comodo Antivirus 7425 and Sophos Anti-Virus 4.61.0 allows remote attackers to bypass malware detection via an Office file with a ustar character sequence at a certain location. NOTE: this may later be SPLIT into multiple CVEs if additional information is...

CVE-2010-3497

Symantec Norton AntiVirus 2011 does not properly interact with the processing of hcp:// URLs by the Microsoft Help and Support Center, which makes it easier for remote attackers to execute arbitrary code via malware that is correctly detected by this product, but with a detection approach that...

CVE-2012-1907

The scanner engine in PrivaWall Antivirus 5.6 and earlier does not recognize the Office XML aka Open Document XML file format, which allows remote attackers to bypass malware detection via a crafted file embedded in a WordML document...

CVE-2012-1430

The ELF file parser in Bitdefender 7.2, Comodo Antivirus 7424, eSafe 7.0.17.0, F-Secure Anti-Virus 9.0.16160.0, McAfee Anti-Virus Scanning Engine 5.400.0.1158, McAfee Gateway formerly Webwasher 2010.1C, nProtect Anti-Virus 2011-01-17.01, Sophos Anti-Virus 4.61.0, and Rising Antivirus 22.83.00.03...

CVE-2010-5179

Race condition in Trend Micro Internet Security Pro 2010 17.50.1647.0000 on Windows XP allows local users to bypass kernel-mode hook handlers, and execute dangerous code that would otherwise be blocked by a handler but not blocked by signature-based malware detection, via certain user-space memor...

CVE-2012-1441

The Microsoft EXE file parser in eSafe 7.0.17.0 and Prevx 3.0 allows remote attackers to bypass malware detection via an EXE file with a modified value in any of several e fields. NOTE: this may later be SPLIT into multiple CVEs if additional information is published showing that the error occurr...

CVE-2012-1436

The Microsoft EXE file parser in AhnLab V3 Internet Security 2011.01.18.00, Emsisoft Anti-Malware 5.1.0.1, eSafe 7.0.17.0, Ikarus Virus Utilities T3 Command Line Scanner 1.1.97.0, and Panda Antivirus 10.0.2.7 allows remote attackers to bypass malware detection via an EXE file with a \2D\6C\68...

Label Studio < 1.18.0 Reflected Cross-Site Scripting

Label Studio versions prior to 1.18.0 are vulnerable to a Reflected Cross-Site Scripting on '/projects/upload-example/' endpoint. This detection is included in the AI and LLM category. No source data...

Can ChatGPT Perform Image Splicing Detection? A Preliminary Study

Multimodal Large Language Models MLLMs like GPT-4V are capable of reasoning across text and image modalities, showing promise in a variety of complex vision-language tasks. In this preliminary study, we investigate the out-of-the-box capabilities of GPT-4V in the domain of image forensics,...

MCP Manifest Detected

This is an informational notice that the scanner was able to detect an MCP Model Context Procol manifest on the target server. No source data...

Advancing Security with Digital Twins: a Comprehensive Survey

The proliferation of electronic devices has greatly transformed every aspect of human life, such as communication, healthcare, transportation, and energy. Unfortunately, the global electronics supply chain is vulnerable to various attacks, including piracy of intellectual properties, tampering,...

Agent2Agent (A2A) Card Detected

This is an informational notice that the scanner was able to detect an Agent2Agent A2A card on the target server. No source data...

When Safety Detectors Aren'T Enough: a Stealthy and Effective Jailbreak Attack on LLMs Via Steganographic Techniques

Jailbreak attacks pose a serious threat to large language models LLMs by bypassing built-in safety mechanisms and leading to harmful outputs. Studying these attacks is crucial for identifying vulnerabilities and improving model security. This paper presents a systematic survey of jailbreak method...