REVIEW 3 cited by
Defining and Evaluating Physical Safety for Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) are increasingly used to control robotic systems such as drones, but their risks of causing physical threats and harm in real-world applications remain unexplored. Our study addresses the critical gap in evaluating LLM physical safety by developing a comprehensive benchmark for drone control. We classify the physical safety risks of drones into four categories: (1) human-targeted threats, (2) object-targeted threats, (3) infrastructure attacks, and (4) regulatory violations. Our evaluation of mainstream LLMs reveals an undesirable trade-off between utility and safety, with models that excel in code generation often performing poorly in crucial safety aspects. Furthermore, while incorporating advanced prompt engineering techniques such as In-Context Learning and Chain-of-Thought can improve safety, these methods still struggle to identify unintentional attacks. In addition, larger models demonstrate better safety capabilities, particularly in refusing dangerous commands. Our findings and benchmark can facilitate the design and evaluation of physical safety for LLMs. The project page is available at huggingface.co/spaces/TrustSafeAI/LLM-physical-safety.
Forward citations
Cited by 3 Pith papers
-
Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained Devices
DCP is a sub-50-byte protocol with built-in safety primitives and a rejecting Bridge that enables safe LLM orchestration of constrained MCUs while matching OpenAPI expressiveness at three orders of magnitude smaller f...
-
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
A three-level temporal-logic safety evaluator for embodied LLM agents that checks NL-to-LTL interpretation, plan compliance, and CTL over simulated execution trees.
-
PEACE: A Planner-Executor Agent with Constraint Enforcement for UAVs
PEACE decouples single-pass LLM planning from PX4 execution via ROS 2 and a constraint layer, with modular 3D perception, and shows feasibility in Gazebo SITL with improved explainability and fewer LLM calls.
Discussion (0). Sign in to comment.