The paper reverse-engineers Apple's Private Cloud Compute (PCC) implementation to independently benchmark its model and evaluate its privacy claims, addressing the lack of transparency in Apple's syst…

The paper proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

This survey reviews hardware-rooted trust mechanisms, such as PUFs and TPMs, demonstrating that hardware-based solutions are superior to software-only methods for ensuring secure authentication and AI…

The paper proposes a co-design paradigm, 'Meeting in the Middle,' to make Fully Homomorphic Encryption (FHE) practical for AI inference by optimizing both the cryptographic schemes and the underlying…

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

This paper conducts a structured ablation study using a unified threat model to evaluate how various system factors (like model architecture and retrieval configuration) influence different types of p…

This paper surveys model forensics in AI-native wireless networks, detailing key security problems and demonstrating practical workflows for verifying model authenticity and detecting malicious functi…

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…

The paper proposes and validates a privacy-preserving framework using Homomorphic Encryption (HE) to train and run Machine Learning models on sensitive data while keeping it encrypted throughout the e…

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…

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 investigates Confused Deputy Attacks (CDAs) on AI Accelerators (AIAs) and finds that CDA is feasible on most major vendor AIAs, impacting a vast number of devices.

This paper provides a comparative analysis and benchmarking of Secure Multi-Party Computation (SMPC) and Fully Homomorphic Encryption (FHE) for machine learning, finding that the optimal choice depend…

The paper proposes a method for bit-exact verification of AI inference outputs without sacrificing performance, demonstrating that deterministic, precise re-computation is possible even across differe…

The paper proposes a privacy-by-design pipeline for Android malware detection that achieves strong performance by avoiding the collection of sensitive user data entirely.

This paper investigates the use of Federated Learning (FL) for hardware assurance, demonstrating that while FL improves model performance over centralized learning, it remains vulnerable to gradient i…

This paper proposes a unified, lifecycle-centric framework and a detailed taxonomy to survey and analyze novel, finance-specific attack surfaces and vulnerabilities in AI systems used within the finan…

The paper introduces extsc{Spore}, a novel, training-free, and highly efficient privacy extraction attack that targets sensitive information stored in the memory of LLM agents during inference, outpe…