Tri-Info uses three information theory signals on action diversity, temporal consistency, and state coupling to predict VLA model failures with cross-domain generalization to 83% real-world accuracy.
Towards robust and secure embodied ai: A survey on vulnerabilities and attacks
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Identifies five attack classes specific to agentic cyber-physical systems and proposes ZTPM with 25 typed primitives across five domains plus Physical Impact Tiers, motivated by 60-trace evidence of model-dependent non-deterministic actuation.
CRA surgically ablates refusal-inducing activation patterns in LLM hidden states during decoding to achieve strong jailbreaks on safety-aligned models.
CMP projects actions onto a learned competence manifold using a frame-wise safety scheme and isomorphic latent space to achieve up to 10x better survival in out-of-distribution scenarios with under 10% tracking loss.
citing papers explorer
-
Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory
Tri-Info uses three information theory signals on action diversity, temporal consistency, and state coupling to predict VLA model failures with cross-domain generalization to 83% real-world accuracy.
-
When Agents Control Robots: A Zero Trust Policy Model for Agentic Cyber-Physical Systems
Identifies five attack classes specific to agentic cyber-physical systems and proposes ZTPM with 25 typed primitives across five domains plus Physical Impact Tiers, motivated by 60-trace evidence of model-dependent non-deterministic actuation.
-
Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation
CRA surgically ablates refusal-inducing activation patterns in LLM hidden states during decoding to achieve strong jailbreaks on safety-aligned models.
-
CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection
CMP projects actions onto a learned competence manifold using a frame-wise safety scheme and isomorphic latent space to achieve up to 10x better survival in out-of-distribution scenarios with under 10% tracking loss.