With ‘TPUXtract,’ Attackers Can Steal Orgs’ AI Models
A new side-channel attack method is a computationally practical way to infer the structure of a convolutional neural network —…
New IOCONTROL malware used in critical infrastructure attacks
Iranian threat actors are utilizing a new malware named IOCONTROL to compromise Internet of Things (IoT) devices and OT/SCADA systems used…
Preparing for EU AI Act from a Security Perspective
The world’s first artificial intelligence law, the EU AI Act, finally came into effect on 1 Aug 2024, 4 years…
Ransomware Gangs Seek Pen Testers to Boost Quality
Qualified applicants must be able to test ransomware encryption and find bugs that might enable defenders to jailbreak the malware.
News Desk 2024: Can GenAI Write Secure Code?
GenAI's 30%-50% coding productivity boost comes with a downside — it's also generating vulnerabilities. Veracode's Chris Wysopal talks about what…
Securing AI Models – Risk and Best Practices
Generative AI (Artificial Intelligence) has turned out to be a game changer after the introduction of ChatGPT, DALL-E, Bard, Gemini,…
Faux ChatGPT, Claude API Packages Deliver JarkaStealer
Attackers are betting that the hype around generative AI (GenAI) is attracting less technical, less cautious developers who might be…
ChatGPT Exposes Its Instructions, Knowledge & OS Files
According to Mozilla, users have a lot more power to manipulate ChatGPT than they might realize. OpenAI hopes those manipulations…
ChatGPT allows access to underlying sandbox OS, “playbook” data
OpenAI's containerized ChatGPT environment is open to limited yet extensive access to core instructions while allowing arbitrary file uploads and…
OpenAI’s new ChatGPT Search Chrome extension feels like a search hijacker
OpenAI's new "ChatGPT search" Chrome extension feels like nothing more than a typical search hijacker, changing Chrome's settings so your address…