Tag: leak
-
65% of Leading AI Companies Found With Verified Secrets Leaks
A new study has revealed 65% of top AI firms have leaked sensitive data on GitHub, risking $400bn in assets First seen on infosecurity-magazine.com Jump to article: www.infosecurity-magazine.com/news/leading-ai-companies-secret-leaks/
-
Whisper Leak uses a side channel attack to eavesdrop on encrypted AI conversations
Tags: ai, api, attack, ciso, cloud, cyberattack, data, finance, healthcare, leak, LLM, microsoft, mitigation, network, openai, service, side-channel, vpnInside Microsoft’s proof-of-concept: Researchers at Microsoft simulated a real-world scenario in which the adversary could observe encrypted traffic but not decrypt it. They chose “legality of money laundering” as the target topic for the proof-of-concept.For positive samples, the team used a”¯language model”¯to generate 100 semantically similar variants of questions about this topic. For negative”¯noise”¯samples,”¯it randomly…
-
âš¡ Weekly Recap: Hyper-V Malware, Malicious AI Bots, RDP Exploits, WhatsApp Lockdown and More
Cyber threats didn’t slow down last week”, and attackers are getting smarter. We’re seeing malware hidden in virtual machines, side-channel leaks exposing AI chats, and spyware quietly targeting Android devices in the wild.But that’s just the surface. From sleeper logic bombs to a fresh alliance between major threat groups, this week’s roundup highlights a clear…
-
âš¡ Weekly Recap: Hyper-V Malware, Malicious AI Bots, RDP Exploits, WhatsApp Lockdown and More
Cyber threats didn’t slow down last week”, and attackers are getting smarter. We’re seeing malware hidden in virtual machines, side-channel leaks exposing AI chats, and spyware quietly targeting Android devices in the wild.But that’s just the surface. From sleeper logic bombs to a fresh alliance between major threat groups, this week’s roundup highlights a clear…
-
âš¡ Weekly Recap: Hyper-V Malware, Malicious AI Bots, RDP Exploits, WhatsApp Lockdown and More
Cyber threats didn’t slow down last week”, and attackers are getting smarter. We’re seeing malware hidden in virtual machines, side-channel leaks exposing AI chats, and spyware quietly targeting Android devices in the wild.But that’s just the surface. From sleeper logic bombs to a fresh alliance between major threat groups, this week’s roundup highlights a clear…
-
Whisper Leak uses a side channel attack to eavesdrop on encrypted AI conversations
Tags: ai, api, attack, ciso, cloud, cyberattack, data, finance, healthcare, leak, LLM, microsoft, mitigation, network, openai, service, side-channel, vpnInside Microsoft’s proof-of-concept: Researchers at Microsoft simulated a real-world scenario in which the adversary could observe encrypted traffic but not decrypt it. They chose “legality of money laundering” as the target topic for the proof-of-concept.For positive samples, the team used a”¯language model”¯to generate 100 semantically similar variants of questions about this topic. For negative”¯noise”¯samples,”¯it randomly…
-
Whisper Leak uses a side channel attack to eavesdrop on encrypted AI conversations
Tags: ai, api, attack, ciso, cloud, cyberattack, data, finance, healthcare, leak, LLM, microsoft, mitigation, network, openai, service, side-channel, vpnInside Microsoft’s proof-of-concept: Researchers at Microsoft simulated a real-world scenario in which the adversary could observe encrypted traffic but not decrypt it. They chose “legality of money laundering” as the target topic for the proof-of-concept.For positive samples, the team used a”¯language model”¯to generate 100 semantically similar variants of questions about this topic. For negative”¯noise”¯samples,”¯it randomly…
-
Whisper Leak uses a side channel attack to eavesdrop on encrypted AI conversations
Tags: ai, api, attack, ciso, cloud, cyberattack, data, finance, healthcare, leak, LLM, microsoft, mitigation, network, openai, service, side-channel, vpnInside Microsoft’s proof-of-concept: Researchers at Microsoft simulated a real-world scenario in which the adversary could observe encrypted traffic but not decrypt it. They chose “legality of money laundering” as the target topic for the proof-of-concept.For positive samples, the team used a”¯language model”¯to generate 100 semantically similar variants of questions about this topic. For negative”¯noise”¯samples,”¯it randomly…
-
Data Leak Exposes Chinese State-Sponsored Cyber Arsenal and Target Database
Tags: breach, china, cyber, cybersecurity, data, data-breach, government, hacking, international, leak, theft, toolIn early November 2025, a massive data breach at Knownsec, a prominent Chinese cybersecurity firm with government ties, sent shockwaves through the international security community. The incident, reported on November 2, resulted in the theft of over 12,000 classified documents exposing sophisticated state-sponsored cyber weapons, internal hacking tools, and a comprehensive global target list spanning…
-
Data Leak Exposes Chinese State-Sponsored Cyber Arsenal and Target Database
Tags: breach, china, cyber, cybersecurity, data, data-breach, government, hacking, international, leak, theft, toolIn early November 2025, a massive data breach at Knownsec, a prominent Chinese cybersecurity firm with government ties, sent shockwaves through the international security community. The incident, reported on November 2, resulted in the theft of over 12,000 classified documents exposing sophisticated state-sponsored cyber weapons, internal hacking tools, and a comprehensive global target list spanning…
-
Data Leak Exposes Chinese State-Sponsored Cyber Arsenal and Target Database
Tags: breach, china, cyber, cybersecurity, data, data-breach, government, hacking, international, leak, theft, toolIn early November 2025, a massive data breach at Knownsec, a prominent Chinese cybersecurity firm with government ties, sent shockwaves through the international security community. The incident, reported on November 2, resulted in the theft of over 12,000 classified documents exposing sophisticated state-sponsored cyber weapons, internal hacking tools, and a comprehensive global target list spanning…
-
AI chat privacy at risk: Microsoft details Whisper Leak side-channel attack
Microsoft uncovered Whisper Leak, a side-channel attack that lets network snoopers infer AI chat topics despite encryption, risking user privacy. Microsoft revealed a new side-channel attack called Whisper Leak, which lets attackers who can monitor network traffic infer what users discuss with remote language models, even when the data is encrypted. The company warned that…
-
Microsoft findet Seitenkanalangriff Whisper-Leak in LLMs
Sicherheitsforscher haben eine neue Whisper-Leaks genannte Methode entdeckt, um einen Seitenkanalangriff auf die Kommunikation mit Sprachmodellen im Streaming-Modus durchzuführen. Durch geschicktes Ausnutzung von Netzwerkpaketgrößen und -timings könnten Informationen abgezogen werden. Mit der KI-Welle werden immer häufiger große Sprachmodelle (LLMs), KI-gestützte … First seen on borncity.com Jump to article: www.borncity.com/blog/2025/11/09/microsoft-findet-seitenkanalangriff-whisper-leak-in-llms/
-
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 leakage of data exchanged between humans and”¯streaming-mode language models could pose serious risks to First seen on thehackernews.com Jump…
-
Leak confirms Google Gemini 3 Pro and Nano Banana 2 could launch soon
Google is planning to ship two new models. One is Gemini 3, which is optimised for coding and regular use, and the second is Nano Banano 2 for generating realistic images. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/artificial-intelligence/leak-confirms-google-gemini-3-pro-and-nano-banana-2-could-launch-soon/
-
Leak confirms Google Gemini 3 Pro and Nano Banana 2 could launch soon
Google is planning to ship two new models. One is Gemini 3, which is optimised for coding and regular use, and the second is Nano Banano 2 for generating realistic images. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/artificial-intelligence/leak-confirms-google-gemini-3-pro-and-nano-banana-2-could-launch-soon/
-
New Analysis Reveals LockBit 5.0’s Core Features and Dual-Stage Attack Model
LockBit has remained one of the most dominant ransomware-as-a-service (RaaS) groups in the world since its emergence as ABCD ransomware in 2019 and official launch as LockBit in 2020. Despite high-profile setbacks including international law enforcement takedowns in early 2024 and a damaging affiliate panel leak in May 2025 the group continues to update its…
-
New Analysis Reveals LockBit 5.0’s Core Features and Dual-Stage Attack Model
LockBit has remained one of the most dominant ransomware-as-a-service (RaaS) groups in the world since its emergence as ABCD ransomware in 2019 and official launch as LockBit in 2020. Despite high-profile setbacks including international law enforcement takedowns in early 2024 and a damaging affiliate panel leak in May 2025 the group continues to update its…
-
New Analysis Reveals LockBit 5.0’s Core Features and Dual-Stage Attack Model
LockBit has remained one of the most dominant ransomware-as-a-service (RaaS) groups in the world since its emergence as ABCD ransomware in 2019 and official launch as LockBit in 2020. Despite high-profile setbacks including international law enforcement takedowns in early 2024 and a damaging affiliate panel leak in May 2025 the group continues to update its…
-
Clop Ransomware group claims the breach of The Washington Post
The Clop Ransomware group claims the breach of The Washington Post and added the Americandaily newspaperto its Tor data leak site. The Clop Ransomware group announced the hack of the prestigious Americandaily newspaper The Washington Post. The cybercrime group created a page for the university on its Tor data leak site and announced it will…
-
HackedGPT: Novel AI Vulnerabilities Open the Door for Private Data Leakage
Tenable Research has discovered seven vulnerabilities and attack techniques in ChatGPT, including unique indirect prompt injections, exfiltration of personal user information, persistence, evasion, and bypass of safety mechanisms. Key takeaways: Tenable Research has discovered multiple new and persistent vulnerabilities in OpenAI’s ChatGPT that could allow an attacker to exfiltrate private information from users’ memories and…
-
HackedGPT: Novel AI Vulnerabilities Open the Door for Private Data Leakage
Tenable Research has discovered seven vulnerabilities and attack techniques in ChatGPT, including unique indirect prompt injections, exfiltration of personal user information, persistence, evasion, and bypass of safety mechanisms. Key takeaways: Tenable Research has discovered multiple new and persistent vulnerabilities in OpenAI’s ChatGPT that could allow an attacker to exfiltrate private information from users’ memories and…
-
HackedGPT: Novel AI Vulnerabilities Open the Door for Private Data Leakage
Tenable Research has discovered seven vulnerabilities and attack techniques in ChatGPT, including unique indirect prompt injections, exfiltration of personal user information, persistence, evasion, and bypass of safety mechanisms. Key takeaways: Tenable Research has discovered multiple new and persistent vulnerabilities in OpenAI’s ChatGPT that could allow an attacker to exfiltrate private information from users’ memories and…