Cybersecurity
Meet the newest AI security threat: token torching
Token torching isn’t your average cyberattack.
AI Threat Detection
Cybersecurity
Threat actors tailor prompt-injection tricks—not for humans, but AI
Phishers want to overwhelm AI-based systems with lots of boring text.
Cybersecurity
Anthropic leak reveals cybersecurity danger and potential of new model
Anthropic claims that the new model can be deployed by attackers to exploit vulnerabilities.
Cybersecurity
AI risks are getting more sophisticated: report
Fragile supply chains, more advanced prompt injections, and the rise of agents are just a few of the risks that AI ecosystems face, according to a new Cisco report.
Cybersecurity
2025 became the year of agentic AI
“Organizations are finally starting to realize that we can’t just rely on AI to self-govern or police its own behavior,” a technical director says.
Cybersecurity
Cisco shows LLMs get worn down by ‘multi-turn’ prompt attacks
It’s “death by a thousand prompts,” the vendor writes in a report released this week.
Cybersecurity
Research: Bad actors could use a ‘bit flip’ attack to deceive AI systems, causing chaos
This threat is not easily discoverable, and solutions have their limitations. How can it be defended against?
Top insights for IT pros
From cybersecurity and big data to cloud computing, IT Brew covers the latest trends shaping business tech in our 4x weekly newsletter, virtual events with industry experts, and digital guides.
By subscribing, you accept our Terms & Privacy Policy.
