7120 matches found
Detecting Data Leaks Before Disaster
In January 2025, cybersecurity experts at Wiz Research found that Chinese AI specialist DeepSeek had suffered a data leak, putting more than 1 million sensitive log streams at risk. According to the Wiz Research team, they identified a publicly accessible ClickHouse database belonging to DeepSeek...
Indirect Prompt Injection Attacks Against LLM Assistants
Really good research on practical attacks against LLM agents. "Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous" Abstract: The growing integration of LLMs into applications has introduced new security risks, notably known as...
Cleartext Storage of Sensitive Information
Overview local-deep-research is an AI-powered research assistant with deep, iterative analysis using LLMs and web searches Affected versions of this package are vulnerable to Cleartext Storage of Sensitive Information in a local SQLite database. An attacker can access sensitive information,...
Local Deep Research 安全漏洞
Local Deep Research is an AI search assistant open-sourced by LearningCircuit. A security vulnerability exists in Local Deep Research 0.6.7 and earlier versions, which stems from unencrypted storage of sensitive information such as API keys, and could lead to a data leak...
HEVD-Exploits
HEVD-Exploits We will exploit HEVD vulner...
The WASM Cloak: Evaluating Browser Fingerprinting Defenses under WebAssembly Based Obfuscation
Browser fingerprinting defenses have historically focused on detecting JavaScriptJS-based tracking techniques. However, the widespread adoption of WebAssembly WASM introduces a potential blind spot, as adversaries can convert JS to WASM's low-level binary format to obfuscate malicious logic. This...
The Era of AI-Generated Ransomware Has Arrived
Cybercriminals are increasingly using generative AI tools to fuel their attacks, with new research finding instances of AI being used to develop ransomware...
77 malicious apps removed from Google Play Store
Google has removed 77 malicious apps from the Google Play Store. Before they were removed, researchers at ThreatLabz discovered the apps had been installed over 19 million times. One of the malware families discovered by the researchers is a banking Trojan known as Anatsa or TeaBot. This banking...
Zeek 8.0.1
Zeek is a powerful network analysis framework that is much different from the typical IDS you may know. While focusing on network security monitoring, Zeek provides a comprehensive platform for more general network traffic analysis as well. Well grounded in more than 15 years of research, Zeek ha...
Encryption Backdoor in Military/Police Radios
I wrote about this in 2023. Here's the story: Three Dutch security analysts discovered the vulnerabilities--five in total--in a European radio standard called TETRA Terrestrial Trunked Radio, which is used in radios made by Motorola, Damm, Hytera, and others. The standard has been used in radio...
Malicious code in seclab-research-depconf-test-2 (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 c4210a0224d23d330894d4d8e0f694f3c81a4fb7b71d5056636aecf98fd9b6f6 Packages that might be part of testing for pentesting / malicious activity / joy, with suspicious activity that does not present any real harm. --- Category:...
MAL-2025-191864 Malicious code in seclab-research-depconf-test-2 (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 c4210a0224d23d330894d4d8e0f694f3c81a4fb7b71d5056636aecf98fd9b6f6 Packages that might be part of testing for pentesting / malicious activity / joy, with suspicious activity that does not present any real harm. --- Category:...
Modern vehicle cybersecurity trends
Modern vehicles are transforming into full-fledged digital devices that offer a multitude of features, from common smartphone-like conveniences to complex intelligent systems and services designed to keep everyone on the road safe. However, this digitalization, while aimed at improving comfort an...
How to Automate Phishing Detection to Prevent Data Theft
Disclosure: This article was provided by ANY.RUN. The information and analysis presented are based on their research and findings...
A Guide to Stakeholder Analysis for Cybersecurity Researchers
Stakeholder-based ethics analysis is now a formal requirement for submissions to top cybersecurity research venues. This requirement reflects a growing consensus that cybersecurity researchers must go beyond providing capabilities to anticipating and mitigating the potential harms thereof. Howeve...
493 Cases of Sextortion Against Children Linked to Notorious Scam Compounds
Scam compounds in Cambodia, Myanmar, and Laos have conned people out of billions. New research shows they may be linked to child sextortion crimes too...
security-research
security-research R...
MAL-2025-32128 Malicious code in research (npm)
The package research was found to contain malicious code...