Cisco Attacks Security Threats With New AI Defense Offering
Cisco's AI Defense offers security teams AI visibility, access control and threat protection for AI security threats.
AI Risks Include Data Poisoning And Model Corruption
When we hear about the risks of AI, we mostly hear about the risks of hallucinations. The risks go much further than that.
It’s remarkably easy to inject new medical misinformation into LLMs
While the paper is focused on the intentional "poisoning" of an LLM during training, it also has implications for the body of ...
New Scientist on MSN14d
Vaccine misinformation can easily poison AI – but there's a fix
Adding just a little medical misinformation to an AI model’s training data increases the chances that chatbots will spew harmful false content about vaccines and other topics ...
OneBlood confirms personal data stolen in July ransomware attack
Blood-donation not-for-profit OneBlood confirms that donors' personal information was stolen in a ransomware attack last ...
Study on medical data finds AI models can easily spread misinformation, even with minimal false input
The study, which focused on medical information, demonstrates that when misinformation accounts for as little as 0.001 ...
Casio says hackers stole personal data of 8,500 people during October ransomware attack
Casio was the target of a ransomware attack on October 5, which saw hackers access sensitive data and render many of the ...
CSOonline7d
Cisco’s homegrown AI to help enterprises navigate AI adoption
Cisco AI Defense is the company’s proprietary AI tool that can validate enterprise AI models and protect them against attacks ...