How Traditional Methods Solve Modern Risks Natural Language Processing and Large Language Models The use of Large Language Models (LLMs) has become widespread and now covers a wide range of applications. However, awareness of the associated security risks is often incomplete. Many language models use chat histories to train newer model versions. As a result,… Continue reading How Traditional Methods Solve Modern Risks
Why We Need to Rethink Penetration Testing for LLMs OVERVIEW Language models and other AI systems behave non-deterministically. The same input can lead to different results depending on context, prompt, or data state. This makes generative AI models powerful — but also unpredictable. And that’s exactly the challenge:Anyone who wants to rely on an AI… Continue reading Why We Need to Rethink Penetration Testing for LLMs
Compliance is not enough – AI needs Security Why AI applications require new protection measures OVERVIEW Sometimes, safety mechanisms in technology fail. In science fiction movies, this is often staged spectacularly – a true classic. In The Day the Earth Stood Still (1951), the robot Gort spirals out of control. The protagonist Helen, however, is… Continue reading Compliance is not enough – AI needs Security
Our Culture as the Engine of Secure LLMs OVERVIEW Technological security does not emerge in a vacuum. It requires not only expertise and methodology, but also attitude, team spirit, and genuine curiosity. For us, culture is not a side effect but a driver – of innovation, of quality, and of our ambition to make language… Continue reading Sequire Culture as the Engine of Secure LLMs
Must AI Obey Humans? When LLMs Act Outside Their Rules OVERVIEW Large language models like ChatGPT are not only changing the way we process information, but also reshaping the security landscape for businesses. New, hard-to-detect risks are emerging – such as so‑called Indirect Prompt Injections, where AI systems are manipulated through seemingly harmless content like… Continue reading When LLMs Get Out of Control: Why Generative AI Needs New Security Rules
Balancing AI Adoption and Risk Awareness in Companies In 2024, sequire was represented at numerous conferences, panels, and workshops. A few examples: Julia Masloh, AI Solution Engineer, joined a panel at the State Chancellery discussing “Artificial Intelligence vs. Real Communication.” Our CEO Dr. Christoph Endres gave over a dozen talks on security vulnerabilities in generative… Continue reading What We Learned in 2024 About AI, Security, and Practical Implementation
The EU rules – you can too! OVERVIEW What will change due to NIS-2 directive? We humans are very evasive about some issues. Of course we want unpleasant incidents to be avoided and for someone to take care of them. This doesn’t necessarily have to be a comic book hero from our childhood; we are… Continue reading NIS-2 directive: What companies need to know and implement
The largest data leaks 2024 CONTENTS AT&T Back in March 2024, a leak from the American internet provider AT&T was published containing the user data of over 73 million AT&T customers. This included names, telephone numbers, addresses, SSNs (Social Security numbers) and poorly encrypted passwords. At least 7.6 million of the passwords, i.e. over 10%,… Continue reading The biggest data leaks in 2024: A review
“Human” gateway for the integration of generativeAI into company systems OVERVIEW Sensitization of employees One of the tasks that I still like to take on myself as Managing Director is securityawareness training. We go to a company or organization and train the employees there ontopics such as secure passwords, Ransomware, browser certificates, email encryption and… Continue reading GenAI: When your employees become a
security risk
From brushstrokes to pixels The parallels between art and IT Art and computer science. At first glance, these two disciplines seem very far apart. But they have more in common than one might think. How do these two areas complement each other? And what is it like to live with one foot in both worlds?… Continue reading Creativity mode “on”: how art and IT complement each other
