Kaspersky

As AI systems based on large language models become more powerful and widespread, more cybersecurity challenges emerge. From jailbreaks to indirect prompt injections, they are vulnerable to a wide array of LLM-specific threats. However, all these problems can be boiled down to one single issue: LLMs are probabilistic algorithms that are inherently unreliable, just like any other ML system. Does it mean they cannot be useful? Absolutely not! In this talk, we will discuss the challenges of secure and reliable LLM-based applications and the way to make them safer and more aligned with your business goals.Presented by Vladislav Tushkanov - Research Development Group Manager | Machine Learning Technology |AI Research | Kaspersky.

In the rapidly shifting world of advanced persistent threats (APTs), tranquility is a rare sight. Leveraging their profound expertise, which includes tracking of hundreds of active APT campaigns, experts from the Kaspersky Global Research and Analysis Team (GReAT) will unveil their insights into the evolving threat landscape in the upcoming year. Join Kaspersky for this webinar, where you will: • Receive a detailed analysis of which of GReAT's predictions from the past year have proven accurate and the underlying factors that contributed to their success or divergence. • Be given forecasts regarding upcoming trends in the realm of APT activity. • Gain insights into the protective measures to counter the ever-evolving threats effectively. Speakers: Igor Kuznetsov, director David Emm, principal security researcher Marc Rivero, lead security researcher Sherif Magdy, senior security researcher Dan Demeter, senior security researcher Global Research and Analysis Team, Kaspersky