Upstream CEO: hacked robots can turn dangerous without losing control
TechNadu · x · 2026-10-22
In a TechNadu interview, Upstream Security CEO Yoav Levy explains how manipulated sensor data or AI instructions can make robots and drones behave unsafely — attackers can trigger dangerous behaviors via valid operational commands without breaching the device.
Levy advocates live digital twins to maintain stateful context, establish behavioral baselines, and detect micro-deviations in real time. He also notes the EU Cyber Resilience Act's mandatory 24-hour reporting window requires fleet-wide continuous visibility to trace supply chain vulnerabilities.
More from Embodied
- 158 of 188 RFD4-Proteina-designed TrkA binders hit sub-micromolar affinity in the lab — AllThingsApx · 2026-10-22
- Team spends $5K benchmarking GPT, Claude, Gemini on LIBERO-10 — best success rate just 44% — YuXiang_IRVL · 2026-10-22
- NVIDIA's Boris Ivanovic talks embodied reasoning models for physical AI at Mila seminar — GlenBerseth · 2026-10-22
- Xpeng's He Xiaopeng: IRON humanoid robot's natural interaction starts with simple moments — Scobleizer · 2026-10-22
- Stanford opens its robot autonomy course materials: free PoRA textbook and lectures for everyone — drmapavone · 2026-10-22
- DONIC: one policy learns dexterous bimanual manipulation, zero fine-tuning — liuziwei7 · 2026-10-22