AI Security ‘Is a Software Problem’
Securing AI systems and LLMs seems like a daunting task, but experts say the same principles that apply to software security can
He is one of the co-founders of Threatpost and previously wrote for TechTarget and eWeek, when magazines were still a thing that existed. Dennis enjoys finding the stories behind the headlines and digging into the motivations and thinking of both defenders and attackers. His work has appeared in The Boston Globe, The Improper Bostonian, Harvard Business School’s Working Knowledge, and most of his kids’ English papers.
Securing AI systems and LLMs seems like a daunting task, but experts say the same principles that apply to software security can
Edge devices have become the go-to targets for cybercriminals and state actors, and experts say that will continue for the
The Verizon 2024 Data Breach Investigations Report shows a 180 percent increase in the use of vulnerability exploits in breaches
ICS and operational technology experts told Congress Tuesday that adversaries' focus on critical infrastructure attacks requires a better focus on the security of these networks by defenders and regulators.
Software security and AI security expert Gary McGraw joins Dennis Fisher to discuss the findings of a new AI architectural risk analysis research paper that his Berryville Institute of Machine Learning did on LLMs, the risks of black box models, and what kind of regulation would be most effective at reducing those risks.
The Department of Justice has disrupted an attack campaign by Chinese state-sponsored attackers on U.S. critical infrastrucutre and says that country's targeting of civilian resources is a "low blow".
Kevin Tian and Rahhul Madduluri, co-founders of Doppel, join Dennis Fisher to discuss the emerging threats of AI-enabled phishing and brand impersonation and how AI can also be used to detect and stop these attacks.
The development and deployment of AI systems based on LLMs includes many inherent risks and should be regulated, and soon, experts say.