7621 matches found
CVE-2025-11210
Side-channel information leakage in Tab in Google Chrome prior to 141.0.7390.54 allowed a remote attacker who convinced a user to engage in specific UI gestures to perform UI spoofing via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11207
Side-channel information leakage in Storage in Google Chrome prior to 141.0.7390.54 allowed a remote attacker to perform arbitrary read/write via a crafted HTML page. Chromium security severity: Medium...
Fedora 42 : cef (2025-313f6d7702)
The remote Fedora 42 host has a package installed that is affected by multiple vulnerabilities as referenced in the FEDORA-2025-313f6d7702 advisory. Update to 141.0.7390.122 High CVE-2025-12036 chromium: Inappropriate implementation in V8 High CVE-2025-11756: Use after free in Safe Browsing High...
Security update for chromium (critical)
openSUSE security update: security update for chromium ------------------------------------------------------------- Announcement ID: openSUSE-SU-2025-20020-1 Rating: critical References: bsc1250472 bsc1250780 bsc1251334 Cross-References: CVE-2025-10890 CVE-2025-10891 CVE-2025-10892 CVE-2025-1120...
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...
PhantomFetch: Obfuscating Loads against Prefetcher Side-Channel Attacks
The IP-stride prefetcher has recently been exploited to leak secrets through side-channel attacks. It, however, cannot be simply disabled for security with prefetching speedup as a sacrifice. The state-of-the-art defense tries to retain the prefetching effect by hardware modification. In this...
CVE-2025-11207
Side-channel information leakage in Storage in Google Chrome prior to 141.0.7390.54 allowed a remote attacker to perform arbitrary read/write via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11210
Side-channel information leakage in Tab in Google Chrome prior to 141.0.7390.54 allowed a remote attacker who convinced a user to engage in specific UI gestures to perform UI spoofing via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11207
Side-channel information leakage in Storage in Google Chrome prior to 141.0.7390.54 allowed a remote attacker to perform arbitrary read/write via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11210
Side-channel information leakage in Tab in Google Chrome prior to 141.0.7390.54 allowed a remote attacker who convinced a user to engage in specific UI gestures to perform UI spoofing via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11210
Side-channel information leakage in Tab in Google Chrome prior to 141.0.7390.54 allowed a remote attacker who convinced a user to engage in specific UI gestures to perform UI spoofing via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11210
Side-channel information leakage in Tab in Google Chrome prior to 141.0.7390.54 allowed a remote attacker who convinced a user to engage in specific UI gestures to perform UI spoofing via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11207
Side-channel information leakage in Storage in Google Chrome prior to 141.0.7390.54 allowed a remote attacker to perform arbitrary read/write via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11207
Side-channel information leakage in Storage in Google Chrome prior to 141.0.7390.54 allowed a remote attacker to perform arbitrary read/write via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11207
Side-channel information leakage in Storage in Google Chrome prior to 141.0.7390.54 allowed a remote attacker to perform arbitrary read/write via a crafted HTML page. Chromium security severity: Medium...
CVE-2025-11207
CVE-2025-11207 affects Google Chrome/Chromium prior to 141.0.7390.54. A side-channel information leakage in Storage allows a remote attacker to perform arbitrary read/write via a crafted HTML page. CVSSv3.1 base score 6.5 (Network exploit, LOW complexity, No privileges, No user interaction, Confi...
CVE-2025-11207
Side-channel information leakage in Storage in Google Chrome prior to 141.0.7390.54 allowed a remote attacker to perform arbitrary read/write via a crafted HTML page. Chromium security severity: Medium...
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...