KBF uses stable numerical recall near the knowledge boundary to fingerprint and audit black-box LLM APIs, successfully detecting all tested substitutions and some real-world inconsistencies across production endpoints.
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the untrusted software stack. However, these isolation guarantees come at a price in performance, compared to untrusted alternatives. This paper initiates the study of high performance execution of Deep Neural Networks (DNNs) in TEEs by efficiently partitioning DNN computations between trusted and untrusted devices. Building upon an efficient outsourcing scheme for matrix multiplication, we propose Slalom, a framework that securely delegates execution of all linear layers in a DNN from a TEE (e.g., Intel SGX or Sanctum) to a faster, yet untrusted, co-located processor. We evaluate Slalom by running DNNs in an Intel SGX enclave, which selectively delegates work to an untrusted GPU. For canonical DNNs (VGG16, MobileNet and ResNet variants) we obtain 6x to 20x increases in throughput for verifiable inference, and 4x to 11x for verifiable and private inference.
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
SPRINT achieves over 99% attribution accuracy on FFHQ images across multiple model pools while reducing adaptive attack success rates to 1% or below by keeping verification targets secret.
The paper delivers a systematization of knowledge on AI agent-blockchain interactions via a bidirectional trust framework, an Agent-Blockchain Interaction Model, a five-dimensional evaluation lens, and nine identified open problems.
Agentic Witnessing enables privacy-preserving auditing of semantic properties in private data by running an LLM auditor in a TEE that answers binary queries and produces cryptographic transcripts of its reasoning.
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
IDN proposes treating AI intelligence as deliverable network services positioned dynamically across distributed compute environments to improve efficiency, latency, and privacy.
CoreGuard introduces a computation- and communication-efficient protocol claimed to deliver upper-bound security against model stealing for edge-deployed LLMs with negligible overhead.
A survey providing a taxonomy of TEE platforms, an agent-centric threat model, and open challenges for applying confidential computing to secure agentic AI systems.
citing papers explorer
-
KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
KBF uses stable numerical recall near the knowledge boundary to fingerprint and audit black-box LLM APIs, successfully detecting all tested substitutions and some real-world inconsistencies across production endpoints.
-
SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction
SPRINT achieves over 99% attribution accuracy on FFHQ images across multiple model pools while reducing adaptive attack success rates to 1% or below by keeping verification targets secret.
-
Toward Web 4.0: Bidirectional Trust between AI Agents and Blockchain
The paper delivers a systematization of knowledge on AI agent-blockchain interactions via a bidirectional trust framework, an Agent-Blockchain Interaction Model, a five-dimensional evaluation lens, and nine identified open problems.
-
Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing
Agentic Witnessing enables privacy-preserving auditing of semantic properties in private data by running an LLM auditor in a TEE that answers binary queries and produces cryptographic transcripts of its reasoning.
-
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
-
Intelligence Delivery Network: Toward an Internet Architecture for the AI Age
IDN proposes treating AI intelligence as deliverable network services positioned dynamically across distributed compute environments to improve efficiency, latency, and privacy.
-
CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
CoreGuard introduces a computation- and communication-efficient protocol claimed to deliver upper-bound security against model stealing for edge-deployed LLMs with negligible overhead.
-
When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI
A survey providing a taxonomy of TEE platforms, an agent-centric threat model, and open challenges for applying confidential computing to secure agentic AI systems.