Cloud-based AI systems offer significant benefits but also introduce vulnerabilities, making deep neural network (DNN) models susceptible to malicious tampering. This tampering may involve harmful behavior injection or resource reduction, compromising model integrity and performance. To detect model tampering, hard-label fingerprinting techniques generate sensitive samples to probe and reveal tampering. Existing fingerprinting methods are mainly based on gradient-defined sensitivity or decision boundary, with the latter showing a manifest superior detection performance. However, all existing fingerprinting methods either suffer from insufficient sensitivity or incur high computational costs.In this paper, we theoretically analyze the black-box co-optimal tampering detection sensitivity of fingerprint samples in the context of decision boundary and gradient-defined sensitivity. Based on this, we further propose Steep-Decision-Boundary Fingerprinting (SDBF), a novel lightweight approach for hard-label tampering detection that inherently and efficiently combines the strengths of existing fingerprinting techniques. SDBF places fingerprint samples near the steep decision boundary, where the outputs of samples are inherently highly sensitive to tampering. We also design a Max Boundary Coverage Strategy (MBCS), which enhances samples’ diversity over the decision boundary. Theoretical analysis and extensive experimental results show that SDBF outperforms existing SOTA hard-label fingerprinting methods in both sensitivity and efficiency.

Adversarial attacks threaten the integrity of deep neural networks (DNNs), particularly in high-stakes applications. In this paper, we present a novel black-box adversarial attack that leverages the diverse checkpoints generated during a single model’s training trajectory. Unlike conventional ensemble attacks that require multiple surrogate models with diverse architectures, our approach exploits the intrinsic diversity captured over different training stages of a single surrogate model. By decomposing the learned representations into task-intrinsic and task-irrelevant components, we employ an accuracy gap-based selection strategy to identify checkpoints that predominantly capture transferable, task-intrinsic knowledge. Extensive experiments on ImageNet and CIFAR-10 demonstrate that our method consistently outperforms traditional ensemble attacks in terms of transferability, even under resource-constrained and practical settings. This work offers a resource-efficient solution for crafting highly transferable adversarial examples and provides new insights into the dynamics of adversarial vulnerability.

Adversarial examples crafted on one model often exhibit poor transferability to others, hindering their effectiveness in black-box settings. This limitation arises from two key factors: (i) \emph{decision-boundary variation} across models and (ii) \emph{representation drift} in feature space. We address these challenges through a new perspective that frames transferability for \emph{untargeted attacks} as a \emph{consensus-robust optimization} problem: adversarial perturbations should remain effective across a neighborhood of plausible target models. To model this uncertainty, we introduce two complementary perturbation channels: a \emph{parameter channel}, capturing boundary shifts via weight perturbations, and a \emph{representation channel}, addressing feature drift via stochastic blending of clean and adversarial activations. We then propose \emph{CORTA} (COnsensus--Robust Transfer Attack), a lightweight attack instantiated from this robust formulation using two first-order strategies: (i) sensitivity regularization based on the squared Frobenius norm of logits’ Jacobian with respect to weights, and (ii) Monte Carlo sampling for blended feature representations. Our theoretical analysis provides a certified lower bound linking these approximations to the robust objective. Extensive experiments on CIFAR-100 and ImageNet show that CORTA significantly outperforms state-of-the-art transfer-based methods---including ensemble approaches---across CNN and Vision Transformer targets. Notably, CORTA achieves a \emph{19.1 percentage-point gain in transfer success rate over the best prior method} while using only a single surrogate model.

In our increasingly interconnected digital world, face recognition serves as a vital security layer for identity verification. However, impersonation attacks pose a significant threat to face recognition systems. While adversarial attacks have proven effective in impersonation, current methods primarily target face recognition, overlooking other crucial processes in real-world applications, such as action-based liveness detection.To address this gap, we introduce MysticMask, a novel adversarial mask attack designed to penetrate the entire face recognition pipeline for impersonation. MysticMask operates in the 3D domain, leveraging foldable medical face masks that automatically align with facial landmarks, enabling accurate physical simulations. MysticMask attacks all processes in a face recognition system simultaneously, including face detection, action-based liveness detection, and face recognition. Additionally, a landmark alignment technique is proposed to pass action-based liveness detection. Extensive experiments conducted in both simulated 3D and real-world scenarios demonstrate MysticMask’s superiority over state-of-the-art methods.