Microsoft Uncovers 'Whisper Leak' Attack That Identifies AI Chat Topics in Encrypted Traffic

Microsoft has disclosed details of a novel side-channel attack targeting remote language models that could enable a passive adversary with capabilities to observe network traffic to glean details about model conversation topics despite encryption protections under certain circumstances. This...

​​Whisper Leak: A novel side-channel attack on remote language models

Microsoft has discovered a new type of side-channel attack on remote language models. This type of side-channel attack could allow a cyberattacker a position to observe your network traffic to conclude language model conversation topics, despite being end-to-end encrypted via Transport Layer...

​​Whisper Leak: A novel side-channel attack on remote language models

Microsoft has discovered a new type of side-channel attack on remote language models. This type of side-channel attack could allow a cyberattacker a position to observe your network traffic to conclude language model conversation topics, despite being end-to-end encrypted via Transport Layer...

Whisper Leak: A Side-Channel Attack on Large Language Models

Large Language Models LLMs are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that infers user prompt topics from encrypted LLM traffic by...

EUVD-2019-10298

Malware in sbrugna...

EUVD-2017-4622

Malware in sbrugna...

EUVD-2024-31976

Malicious code in bioql PyPI...

EUVD-2025-29025

Malicious code in bioql PyPI...

EUVD-2025-13235

Malicious code in bioql PyPI...

EUVD-2023-40763

Malicious code in bioql PyPI...

EUVD-2023-24364

Malicious code in bioql PyPI...

Inference Attacks on Encrypted Online Voting Via Traffic Analysis

Online voting enables individuals to participate in elections remotely, offering greater efficiency and accessibility in both governmental and organizational settings. As this method gains popularity, ensuring the security of online voting systems becomes increasingly vital, as the systems...

CVE-2025-58781

WTW-EAGLE App does not properly validate server certificates, which may allow a man-in-the-middle attacker to monitor encrypted traffic...

CVE-2025-58781

Vulnerability : CVE-2025-58781 affects the WTW-EAGLE App. The app does not properly validate server certificates, enabling a man-in-the-middle attacker to monitor encrypted traffic. Affected products/versions : WTW-EAGLE App for iOS prior to 4.4.1 and Android prior to 4.4.0.10. Other sources reit...

CVE-2025-58781

WTW-EAGLE App does not properly validate server certificates, which may allow a man-in-the-middle attacker to monitor encrypted traffic...

WTW-EAGLE App 信任管理问题漏洞

WTW-EAGLE App is a mobile application from WTW that has the ability to provide risk management, insurance data access and analytics. A trust management issue vulnerability exists in the WTW-EAGLE App that stems from not properly validating server certificates, which could lead to a...

CVE-2025-58781: Improper Certificate Validation

WTW-EAGLE App does not properly validate server certificates, which may allow a man-in-the-middle attacker to monitor encrypted traffic...

PT-2025-37292

Name of the Vulnerable Software and Affected Versions: WTW-EAGLE App affected versions not specified Description: The WTW-EAGLE App does not properly validate server certificates, potentially allowing a man-in-the-middle attacker to monitor encrypted traffic. Recommendations: At the moment, there...

Can Your Security Stack See ChatGPT? Why Network Visibility Matters

Generative AI platforms like ChatGPT, Gemini, Copilot, and Claude are increasingly common in organizations. While these solutions improve efficiency across tasks, they also present new data leak prevention for generative AI challenges. Sensitive information may be shared through chat prompts, fil...

M3S-UPD: Efficient Multi-Stage Self-Supervised Learning for Fine-Grained Encrypted Traffic Classification with Unknown Pattern Discovery

The growing complexity of encrypted network traffic presents dual challenges for modern network management: accurate multiclass classification of known applications and reliable detection of unknown traffic patterns. Although deep learning models show promise in controlled environments, their...