“Real Attackers Don’t Compute Gradients”: Bridging the Gap Between Adversarial ML Research and Practice

At the Dagstuhl Seminar on Security of Machine Learning in July 2022, experts from all over the world met to discuss research trends and future directions for research in protecting ML-based systems. The seminar featured a mix of academics, young researchers, and industry practitioners. Despite the relaxed atmosphere, the seminar inspired diverse questions—among which, a recurring theme entailed the practical relevance of related research. For example, should industry truly be worried about the attacks portrayed in research papers, and are the assumptions made in research truly representative of the real world?

Bringing Together Research and Practice

Software engineers are in high demand. With numbers of new jobs exploding, there is a real risk of an impossibly complex patchwork of different and competing engineering approaches. Dr Steffen Zschaler and his team have built a new community network that helps academics and practitioners to get together, share best practices and ground their coding methodologies on sound, model-based approaches.