Suggestions
Benji Weber
Technology Leader
Benji Weber is a skilled technical leader with a strong background in building high-performing teams and delivering sustainable value quickly. He is a renowned conference speaker and blogger focusing on Java and Extreme Programming.
Benji studied BSc in Computer Science at the University of Warwick, solidifying his foundation in technology and innovation.
Throughout his career, Benji Weber has held a series of prominent leadership roles in various organizations, showcasing his expertise and proficiency in the tech industry:
-
Former VP of Engineering at Mindgard.
-
Former Senior Director of Engineering at Snyk.
-
Former Director of Engineering at Snyk.
-
Former VP Engineering at Pockit
-
Former SVP Software Development at Unruly.
-
Former VP Software Development at Unruly.
-
Former Product Development Team Leader at Unruly.
-
Former Senior Software Developer / Tech Specialist at Unruly.
-
Former Software Developer at Reed Business Information.
Highlights
Are you using #AI for recognising documents, processing KYC checks, or spotting fraud? Do you know how easily it can be bypassed?
At Mindgard our team recently made freely available a sample of our library of attack techniques for image models via our public CLI. Try it out and see how Mindgard can help find and mitigate risks to your Predictive AI as well as GenAI.
#AISecurity risks need managing for Predictive AI as well as GenAI, and indeed multi-modal and composite models. Mindgard is uniquely able to test any neural network against a wide variety of threats.
Nice segment on BBC news tonight that explains why Mindgard 's work is so important. We're helping organisations adopt AI without fear of these risks, through tooling that gives visibility, mitigations, and ability to manage these risks without having to hire expert red teams.
"how long would it take an advanced hacker to break into the most complex, most powerful AI models…30 minutes, as it happens"
"[AI adoption] it's always going to be an unknown risk. You're giving up your data, your property, your brand reputation, and you're putting into a system that you're hoping is going to protect and secure it "
"organisations need to be aware of the risks that they are taking around [AI], organisations don't yet know what those risks are"
"none of our methods are adequate, not whatsoever… our understanding of what AI models do internally is extremely inadequate compared to our understanding of other types of software systems and even with other types of software systems our safety is very shaky"
"if we are integrating this technology into our critical systems then this becomes really serious"
