The paper proves that platform-deterministic inference is a necessary and sufficient condition for trustworthy AI, establishing that AI trust fundamentally relies on consistent arithmetic.

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

Hawkeye is a system that allows perfect, precision-preserving reproduction of GPU-level matrix multiplication operations on a CPU, enabling efficient and trustworthy third-party auditing of machine le…

This paper introduces a fingerprinting method that exploits subtle numerical deviations in the inference system components (like the engine or hardware) to reliably identify the specific components us…

This paper introduces a dual-layer side-channel attack framework that exploits the variable workload introduced by dynamic image preprocessing in local Vision-Language Models (VLMs) to infer sensitive…

This survey reviews the integration of AI and LLMs into hardware security verification, demonstrating its potential to automate complex stages while stressing the necessity of grounding AI outputs in…

This paper presents a novel data-free Membership Inference Attack (MIA) that uses gradient inversion on Standard Cell Library Layouts (SCLLs) to reconstruct sensitive hardware images from intercepted…

The paper introduces a framework, PD-FHC, that allows users to outsource Boolean computations to an untrusted cloud while guaranteeing both computational privacy and plausible deniability against coer…

The paper introduces AutoMIA, a novel framework that uses LLM agents to automate the discovery and implementation of Membership Inference Attacks (MIAs), achieving state-of-the-art performance by syst…

This paper analyzes the reliability of efficient membership inference attack (MIA) evaluation methods, demonstrating that standard aggregation techniques introduce biases that compromise accurate vuln…

The paper introduces a novel threat model, approximate obfuscation, and proposes a framework to detect IP piracy in approximate circuits by comparing their statistical error profiles.

The paper proposes a hybrid ASIC+eFPGA architecture to enhance the security and resilience of edge LLM inference accelerators against both runtime and supply-chain attacks.

This paper introduces a novel class of backdoor attacks that exploit the numerical side effects of LLM inference optimization, achieving high success rates while maintaining clean accuracy.

This paper provides the first comprehensive review of threats and defenses specifically targeting on-device AI inference, revealing a significant imbalance where certain attack types, like adversarial…

EncFormer is a novel two-party framework that significantly improves the efficiency and scalability of private Transformer inference by optimizing the combination of Fully Homomorphic Encryption (FHE)…

The paper proposes Agentic Witnessing, a TEE-enabled framework that allows external verifiers to audit the qualitative properties of private datasets by querying an LLM-based auditor without accessing…

The paper introduces ACE, a novel voting protocol that achieves end-to-end verifiability and strong voter privacy by combining tally-hiding aggregation with an Audit-or-Cast challenge, eliminating the…

The paper proposes a tamper-proofing model for self-modifying code (SMC) by leveraging external timing, concurrency, and microarchitectural state to make non-SMC reproduction detectably expensive.

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

NANOZK introduces a novel, highly efficient zero-knowledge proof system that allows users to cryptographically verify that the output of a large language model (LLM) was generated by a specific, claim…