More results...
Attackers intercepting network traffic can determine the conversation topic with a chatbot despite end-to-end encrypted communication.
The post ‘Whisper Leak’ LLM Side-Channel Attack Infers User Prompt Topics appeared first on SecurityWeek.
This is why AIs are not ready to be personal assistants:
A new attack called ‘CometJacking’ exploits URL parameters to pass to Perplexity’s Comet AI browser hidden instructions that allow access to sensitive data from connected services, like email and calendar.
In a realistic scenario, no credentials or user interaction are required and a threat actor can leverage the attack by simply exposing a maliciously crafted URL to targeted users.
[…]
CometJacking is a prompt-injection attack where the query string processed by the Comet AI browser contains malicious instructions added using the ‘collection’ parameter of the URL…
Cisco’s new research shows that open-weight AI models, while driving innovation, face serious security risks as multi-turn attacks, including conversational persistence, can bypass safeguards and expose data.
A comprehensive security analysis has uncovered a troubling reality: 65% of leading AI companies have leaked verified secrets on GitHub, exposing critical API keys, authentication tokens, and sensitive credentials that could compromise their entire org…
Wiz found the secrets and warned that they can expose training data, organizational structures, and private models.
The post Many Forbes AI 50 Companies Leak Secrets on GitHub appeared first on SecurityWeek.
With a 4M cybersecurity worker shortage, agentic AI helps SOCs move beyond triage, enabling proactive security once thought impossible. With a deficit of 4 million cybersecurity workers worldwide, it’s no surprise that most SOCs are still stuck in triage mode. That’s why agentic AI is stepping in to fill the gap. And this boost to […]
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 […]
US Ambassador to India, Vinay Mohan Kwatra, held a strategic meeting with Intel CEO, Lip Bu Tan, in Washington DC to deepen collaboration between the global tech giant and India’s semiconductor and Artificial Intelligence ecosystem.The interaction focused on aligning Intel’s India expansion with the Government’s vision under the India Semiconductor Mission (ISM) and the India AI Mission.In a post
The vulnerability is tracked as CVE-2025-12058 and it can be exploited for arbitrary file loading and conducting SSRF attacks.
The post Data Exposure Vulnerability Found in Deep Learning Tool Keras appeared first on SecurityWeek.
Over the past few decades, it’s become easier and easier to create fake receipts. Decades ago, it required special paper and printers—I remember a company in the UK advertising its services to people trying to cover up their affairs. Then, receipts became computerized, and faking them required some artistic skills to make the page look realistic.
Now, AI can do it all:
Several receipts shown to the FT by expense management platforms demonstrated the realistic nature of the images, which included wrinkles in paper, detailed itemization that matched real-life menus, and signatures…