Alignment contracts define scope, allowed effects, budgets and disclosure rules as safety properties over finite effect traces, with decidable admissibility, refinement rules, and Lean-verified soundness under an observability assumption.
Can we trust embodied agents? exploring backdoor attacks against embodied llm-based decision-making systems
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 3roles
dataset 1polarities
use dataset 1representative citing papers
Injecting brief safety-plausible phrases into robot audio triggers LLM safety halts, enabling semantic denial-of-service attacks where prompt defenses trade attack suppression for impaired genuine hazard detection.
PRA-RAG is a new aggregation algorithm for RAG that claims provable robustness bounds against poisoned retrieved texts and reduces attack success rate to 1% while keeping 71% accuracy.
citing papers explorer
-
Alignment Contracts for Agentic Security Systems
Alignment contracts define scope, allowed effects, budgets and disclosure rules as safety properties over finite effect traces, with decidable admissibility, refinement rules, and Lean-verified soundness under an observability assumption.
-
Semantic Denial of Service in LLM-controlled robots
Injecting brief safety-plausible phrases into robot audio triggers LLM safety halts, enabling semantic denial-of-service attacks where prompt defenses trade attack suppression for impaired genuine hazard detection.
-
PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption
PRA-RAG is a new aggregation algorithm for RAG that claims provable robustness bounds against poisoned retrieved texts and reduces attack success rate to 1% while keeping 71% accuracy.