arXiv subjects

Yunsi Fei

Publications and source records attributed to Yunsi Fei.

At least 19 recordsLinked to original sources

arXiv2026

Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips

Mixture-of-Experts (MoE) architectures enable scalable and efficient large language models (LLMs) by selectively activating expert sub-networks through a routing mechanism. However, this adaptive design introduces a new attack surface: specific experts become disproportionately correlated with certain tokens (e.g., end-of-sequence), allowing adversaries to manipulate model behavior via lightweight perturbations. In this work, we present \textbf{Groundhog Bit-Flip Attack (GBFA)}, the first bit-flip-based \textit{ Denial-of-Wallet availability attack} against MoE-based LLMs. By identifying and flipping routing-layer bits associated with related expert activations, we demonstrate that GBFA substantially extends the decoding token usage across three different LLM modes: conversational, reasoning, and agentic tasks, while largely preserving semantic fidelity. Across four main real-world MoE-based LLMs, manually deactivating on average fewer than \textbf{4 experts} drives average output inflation to $\mathbf{5912\%}$, with the majority of test samples reaching max tokens. These results reveal a robustness vulnerability of MoE architectures to bit flip, and highlight the potential of GBFA as an availability attack against LLMs.

cs.CL↗

arXiv2026

ROBBIN: Rowhammer-Based Backdoor Injection during Inference

Existing Rowhammer-based inference-time backdoor attacks design their bit-flip strategies purely at the algorithmic level, without accounting for the bit-flips that the underlying DRAM hardware will actually produce. This disconnection between the algorithmic backdoor construction and its hardware realization leads to unreliable attack performance, as collateral bit-flips at unintended locations degrade both the attack success rate (ASR) on triggered inputs and the test accuracy (TA) for normal inputs. Consequently, the performance of such attacks varies significantly across different DRAM devices, as each device presents a unique set of exploitable bit-flip locations. This work presents ROBBIN, a hardware-aware Rowhammer-based backdoor injection attack that integrates the device-specific vulnerability into the backdoor construction process. ROBBIN first characterizes the bit-flip patterns of a target DRAM and uses this information to iteratively select DRAM \textit{page} mappings for the model weights that would maximize ASR while preserving TA under Rowhammering. By treating every hammering-induced bit-flip as an integral part of the attack design rather than first constructing a hardware-agnostic backdoor and dismissing collateral flips as side effects, ROBBIN produces backdoors that remain robust across devices. Evaluated on ResNet-20 and VGG-16 with CIFAR-10 across three commodity DDR4 chips, ROBBIN consistently achieves close to 90\% ASR while maintaining TA above 83\%, demonstrating reliable backdoor efficacy across diverse DRAM devices.

cs.CR↗

arXiv2026

SLAC: Access-Driven CPU-to-GPU Side-channel Attacks via System-Level Cache on Apple Silicon

Modern heterogeneous System-on-Chip designs integrate CPU cores and a GPU that share a last-level cache (LLC) or system-level cache (SLC). This sharing exposes a new cross-domain attack surface, and existing attacks on integrated platforms either exploit coarse-grained cache-occupancy contention or require the adversary to co-reside on the GPU with the victim to obtain accurate timing measurements. In this work, we target Apple Silicon heterogeneous SoCs and discover that GPU memory accesses leave set-level footprints in the shared SLC, observable to an unprivileged CPU process. This keen observation enables the first fine-grained, access-driven, Prime+Probe-style CPU-to-GPU cache side-channel attacks against GPU workloads. We first reverse-engineer the Apple M1 SLC set-indexing functions and the interactions between local private caches and the SLC. Building on these findings, we construct the CPrime+CProbe SLC side-channel technique, which monitors GPU victim activity from the CPU at cache-set granularity. We then introduce an accelerated variant, GPrime+CProbe, in which an adversary leverages the GPU for faster SLC priming, yielding a 6.4x increase in the covert-channel throughput. Lastly, we demonstrate two end-to-end privacy attacks using the new side-channels: a graph-edge reconstruction attack on Graph Neural Networks (GNNs) that achieves 90% edge accuracy across five datasets, and an LLM privacy attack that recovers input keywords with up to 94.8% accuracy and model responses with up to 88.9% accuracy across TinyLlama and GPT-2 Medium models. Our results reveal a new class of microarchitectural vulnerabilities in Apple Silicon and call for secure system cache designs for heterogeneous SoCs.

cs.CR↗

arXiv2026

Exploring Side-Channel Protections in Hardware Implementations of PQC ML-KEM Verification

As ML-KEM is adopted as a post-quantum cryptographic standard, resilience against physical side-channel attacks has become essential. Among the constituent steps, the decapsulation Fujisaki-Okamoto (FO) verification is particularly vulnerable to side-channel power and electromagnetic (EM) analysis. In this work, we focus on common FPGA-based implementations and examine their side-channel vulnerabilities, and compare them with those of microcontroller implementations. Three verification implementations, unprotected, hash-based (first-order), and higher-order masked, are evaluated for side-channel security on both a microcontroller and an FPGA. While FPGAs offer higher speed and parallelism, they often exhibit stronger side-channel leakage, especially in high bandwidth configurations. The higher-order masked designs still leak information about the underlying data due to hardware-level effects and data-dependent processing. Our experiments show that their parallelized processing on FPGAs introduces sufficient first-order leakage for full secret-key recovery. These results underscore the persistent challenge of securing PQC algorithms in performance-constrained and parallelized hardware environments.

cs.CR↗

arXiv2025

MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks

The rapid growth of digital and AI-generated images has amplified the need for secure and verifiable methods of image attribution. While digital watermarking offers more robust protection than metadata-based approaches--which can be easily stripped--current watermarking techniques remain vulnerable to forgery, creating risks of misattribution that can damage the reputations of AI model developers and the rights of digital artists. The vulnerabilities of digital watermarking arise from two key issues: (1) content-agnostic watermarks, which, once learned or leaked, can be transferred across images to fake attribution, and (2) reliance on detector-based verification, which is unreliable since detectors can be tricked. We present MetaSeal, a novel framework for content-dependent watermarking with cryptographic security guarantees to safeguard image attribution. Our design provides (1) \textbf{forgery resistance}, preventing unauthorized replication and enforcing cryptographic verification; (2) \textbf{robust self-contained protection}, embedding attribution directly into images while maintaining robustness against benign transformations; and (3) \textbf{evidence of tampering}, making malicious alterations visually detectable. Experiments demonstrate that MetaSeal effectively mitigates forgery attempts and applies to both natural and AI-generated images, establishing a new standard for secure image attribution. Code is available at: https://github.com/Tongzhou0101/MetaSeal.

cs.CR↗

arXiv2025

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs

The transformer architecture has become a cornerstone of modern AI, fueling remarkable progress across applications in natural language processing, computer vision, and multimodal learning. As these models continue to scale explosively for performance, implementation efficiency remains a critical challenge. Mixture of Experts (MoE) architectures, selectively activating specialized subnetworks (experts), offer a unique balance between model accuracy and computational cost. However, the adaptive routing in MoE architectures, where input tokens are dynamically directed to specialized experts based on their semantic meaning inadvertently opens up a new attack surface for privacy breaches. These input-dependent activation patterns leave distinctive temporal and spatial traces in hardware execution, which adversaries could exploit to deduce sensitive user data. In this work, we propose MoEcho, discovering a side channel analysis based attack surface that compromises user privacy on MoE based systems. Specifically, in MoEcho, we introduce four novel architectural side channels on different computing platforms, including Cache Occupancy Channels and Pageout+Reload on CPUs, and Performance Counter and TLB Evict+Reload on GPUs, respectively. Exploiting these vulnerabilities, we propose four attacks that effectively breach user privacy in large language models (LLMs) and vision language models (VLMs) based on MoE architectures: Prompt Inference Attack, Response Reconstruction Attack, Visual Inference Attack, and Visual Reconstruction Attack. MoEcho is the first runtime architecture level security analysis of the popular MoE structure common in modern transformers, highlighting a serious security and privacy threat and calling for effective and timely safeguards when harnessing MoE based models for developing efficient large scale AI services.

cs.CR↗

arXiv2025

Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks

Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability.We propose the fault sneaking attack on DNNs, where the adversary aims to misclassify certain input images into any target labels by modifying the DNN parameters. We apply ADMM (alternating direction method of multipliers) for solving the optimization problem of the fault sneaking attack with two constraints: 1) the classification of the other images should be unchanged and 2) the parameter modifications should be minimized. Specifically, the first constraint requires us not only to inject designated faults (misclassifications), but also to hide the faults for stealthy or sneaking considerations by maintaining model accuracy. The second constraint requires us to minimize the parameter modifications (using L0 norm to measure the number of modifications and L2 norm to measure the magnitude of modifications). Comprehensive experimental evaluation demonstrates that the proposed framework can inject multiple sneaking faults without losing the overall test accuracy performance.

cs.LG↗

arXiv2025

EXAM: Exploiting Exclusive System-Level Cache in Apple M-Series SoCs for Enhanced Cache Occupancy Attacks

Cache occupancy attacks exploit the shared nature of cache hierarchies to infer a victim's activities by monitoring overall cache usage, unlike access-driven cache attacks that focus on specific cache lines or sets. There exists some prior work that target the last-level cache (LLC) of Intel processors, which is inclusive of higher-level caches, and L2 caches of ARM systems. In this paper, we target the System-Level Cache (SLC) of Apple M-series SoCs, which is exclusive to higher-level CPU caches. We address the challenges of the exclusiveness and propose a suite of SLC-cache occupancy attacks, the first of its kind, where an adversary can monitor GPU and other CPU cluster activities from their own CPU cluster. We first discover the structure of SLC in Apple M1 SOC and various policies pertaining to access and sharing through reverse engineering. We propose two attacks against websites. One is a coarse-grained fingerprinting attack, recognizing which website is accessed based on their different GPU memory access patterns monitored through the SLC occupancy channel. The other attack is a fine-grained pixel stealing attack, which precisely monitors the GPU memory usage for rendering different pixels, through the SLC occupancy channel. Third, we introduce a novel screen capturing attack which works beyond webpages, with the monitoring granularity of 57 rows of pixels (there are 1600 rows for the screen). This significantly expands the attack surface, allowing the adversary to retrieve any screen display, posing a substantial new threat to system security. Our findings reveal critical vulnerabilities in Apple's M-series SoCs and emphasize the urgent need for effective countermeasures against cache occupancy attacks in heterogeneous computing environments.

cs.CR↗

arXiv2025

USBSnoop -- Revealing Device Activities via USB Congestions

The USB protocol has become a ubiquitous standard for connecting peripherals to computers, making its security a critical concern. A recent research study demonstrated the potential to exploit weaknesses in well-established protocols, such as PCIe, and created a side-channel for leaking sensitive information by leveraging congestion within shared interfaces. Drawing inspiration from that, this project introduces an innovative approach to USB side-channel attacks via congestion. We evaluated the susceptibility of USB devices and hubs to remote profiling and side-channel attacks, identified potential weaknesses within the USB standard, and highlighted the critical need for heightened security and privacy in USB technology. Our findings discover vulnerabilities within the USB standard, which are difficult to effectively mitigate and underscore the need for enhanced security measures to protect user privacy in an era increasingly dependent on USB-connected devices.

cs.CR↗

arXiv2025

Graph in the Vault: Protecting Edge GNN Inference with Trusted Execution Environment

Wide deployment of machine learning models on edge devices has rendered the model intellectual property (IP) and data privacy vulnerable. We propose GNNVault, the first secure Graph Neural Network (GNN) deployment strategy based on Trusted Execution Environment (TEE). GNNVault follows the design of 'partition-before-training' and includes a private GNN rectifier to complement with a public backbone model. This way, both critical GNN model parameters and the private graph used during inference are protected within secure TEE compartments. Real-world implementations with Intel SGX demonstrate that GNNVault safeguards GNN inference against state-of-the-art link stealing attacks with negligible accuracy degradation (<2%).

cs.CR↗

arXiv2025

MACPruning: Dynamic Operation Pruning to Mitigate Side-Channel DNN Model Extraction

As deep learning gains popularity, edge IoT devices have seen proliferating deployment of pre-trained Deep Neural Network (DNN) models. These DNNs represent valuable intellectual property and face significant confidentiality threats from side-channel analysis (SCA), particularly non-invasive Differential Electromagnetic (EM) Analysis (DEMA), which retrieves individual model parameters from EM traces collected during model inference. Traditional SCA mitigation methods, such as masking and shuffling, can still be applied to DNN inference, but will incur significant performance degradation due to the large volume of operations and parameters. Based on the insight that DNN models have high redundancy and are robust to input variation, we introduce MACPruning, a novel lightweight defense against DEMA-based parameter extraction attacks, exploiting specific characteristics of DNN execution. The design principle of MACPruning is to randomly deactivate input pixels and prune the operations (typically multiply-accumulate-MAC) on those pixels. The technique removes certain leakages and overall redistributes weight-dependent EM leakages temporally, and thus effectively mitigates DEMA. To maintain DNN performance, we propose an importance-aware pixel map that preserves critical input pixels, keeping randomness in the defense while minimizing its impact on DNN performance due to operation pruning. We conduct a comprehensive security analysis of MACPruning on various datasets for DNNs on edge devices. Our evaluations demonstrate that MACPruning effectively reduces EM leakages with minimal impact on the model accuracy and negligible computational overhead.

cs.CR↗

arXiv2024

Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing

Adapting pre-trained deep learning models to customized tasks has become a popular choice for developers to cope with limited computational resources and data volume. More specifically, probing--training a downstream head on a pre-trained encoder--has been widely adopted in transfer learning, which helps to prevent overfitting and catastrophic forgetting. However, such generalizability of pre-trained encoders raises concerns about the potential misuse of probing for harmful intentions, such as discriminatory speculation and warfare applications. In this work, we introduce EncoderLock, a novel applicability authorization method designed to protect pre-trained encoders from malicious probing, i.e., yielding poor performance on specified prohibited domains while maintaining their utility in authorized ones. Achieving this balance is challenging because of the opposite optimization objectives and the variety of downstream heads that adversaries can utilize adaptively. To address these challenges, EncoderLock employs two techniques: domain-aware weight selection and updating to restrict applications on prohibited domains/tasks, and self-challenging training scheme that iteratively strengthens resistance against any potential downstream classifiers that adversaries may apply. Moreover, recognizing the potential lack of data from prohibited domains in practical scenarios, we introduce three EncoderLock variants with different levels of data accessibility: supervised (prohibited domain data with labels), unsupervised (prohibited domain data without labels), and zero-shot (no data or labels available). We verify EncoderLock's effectiveness and practicality with a real-world pre-trained Vision Transformer (ViT) encoder from Facebook. These results underscore the valuable contributions EncoderLock brings to the development of responsible AI.

cs.CR↗

arXiv2024

Non-transferable Pruning

Pretrained Deep Neural Networks (DNNs), developed from extensive datasets to integrate multifaceted knowledge, are increasingly recognized as valuable intellectual property (IP). To safeguard these models against IP infringement, strategies for ownership verification and usage authorization have emerged. Unlike most existing IP protection strategies that concentrate on restricting direct access to the model, our study addresses an extended DNN IP issue: applicability authorization, aiming to prevent the misuse of learned knowledge, particularly in unauthorized transfer learning scenarios. We propose Non-Transferable Pruning (NTP), a novel IP protection method that leverages model pruning to control a pretrained DNN's transferability to unauthorized data domains. Selective pruning can deliberately diminish a model's suitability on unauthorized domains, even with full fine-tuning. Specifically, our framework employs the alternating direction method of multipliers (ADMM) for optimizing both the model sparsity and an innovative non-transferable learning loss, augmented with Fisher space discriminative regularization, to constrain the model's generalizability to the target dataset. We also propose a novel effective metric to measure the model non-transferability: Area Under the Sample-wise Learning Curve (SLC-AUC). This metric facilitates consideration of full fine-tuning across various sample sizes. Experimental results demonstrate that NTP significantly surpasses the state-of-the-art non-transferable learning methods, with an average SLC-AUC at $-0.54$ across diverse pairs of source and target domains, indicating that models trained with NTP do not suit for transfer learning to unauthorized target domains. The efficacy of NTP is validated in both supervised and self-supervised learning contexts, confirming its applicability in real-world scenarios.

cs.LG↗

arXiv2024

GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction

Graph-structured data is integral to many applications, prompting the development of various graph representation methods. Graph autoencoders (GAEs), in particular, reconstruct graph structures from node embeddings. Current GAE models primarily utilize self-correlation to represent graph structures and focus on node-level tasks, often overlooking multi-graph scenarios. Our theoretical analysis indicates that self-correlation generally falls short in accurately representing specific graph features such as islands, symmetrical structures, and directional edges, particularly in smaller or multiple graph contexts. To address these limitations, we introduce a cross-correlation mechanism that significantly enhances the GAE representational capabilities. Additionally, we propose GraphCroc, a new GAE that supports flexible encoder architectures tailored for various downstream tasks and ensures robust structural reconstruction, through a mirrored encoding-decoding process. This model also tackles the challenge of representation bias during optimization by implementing a loss-balancing strategy. Both theoretical analysis and numerical evaluations demonstrate that our methodology significantly outperforms existing self-correlation-based GAEs in graph structure reconstruction.

cs.LG↗

arXiv2023

VertexSerum: Poisoning Graph Neural Networks for Link Inference

Graph neural networks (GNNs) have brought superb performance to various applications utilizing graph structural data, such as social analysis and fraud detection. The graph links, e.g., social relationships and transaction history, are sensitive and valuable information, which raises privacy concerns when using GNNs. To exploit these vulnerabilities, we propose VertexSerum, a novel graph poisoning attack that increases the effectiveness of graph link stealing by amplifying the link connectivity leakage. To infer node adjacency more accurately, we propose an attention mechanism that can be embedded into the link detection network. Our experiments demonstrate that VertexSerum significantly outperforms the SOTA link inference attack, improving the AUC scores by an average of $9.8\%$ across four real-world datasets and three different GNN structures. Furthermore, our experiments reveal the effectiveness of VertexSerum in both black-box and online learning settings, further validating its applicability in real-world scenarios.

cs.LG↗

arXiv2023

EMShepherd: Detecting Adversarial Samples via Side-channel Leakage

Deep Neural Networks (DNN) are vulnerable to adversarial perturbations-small changes crafted deliberately on the input to mislead the model for wrong predictions. Adversarial attacks have disastrous consequences for deep learning-empowered critical applications. Existing defense and detection techniques both require extensive knowledge of the model, testing inputs, and even execution details. They are not viable for general deep learning implementations where the model internal is unknown, a common 'black-box' scenario for model users. Inspired by the fact that electromagnetic (EM) emanations of a model inference are dependent on both operations and data and may contain footprints of different input classes, we propose a framework, EMShepherd, to capture EM traces of model execution, perform processing on traces and exploit them for adversarial detection. Only benign samples and their EM traces are used to train the adversarial detector: a set of EM classifiers and class-specific unsupervised anomaly detectors. When the victim model system is under attack by an adversarial example, the model execution will be different from executions for the known classes, and the EM trace will be different. We demonstrate that our air-gapped EMShepherd can effectively detect different adversarial attacks on a commonly used FPGA deep learning accelerator for both Fashion MNIST and CIFAR-10 datasets. It achieves a 100% detection rate on most types of adversarial samples, which is comparable to the state-of-the-art 'white-box' software-based detectors.

cs.CR↗

arXiv2022

NNReArch: A Tensor Program Scheduling Framework Against Neural Network Architecture Reverse Engineering

Architecture reverse engineering has become an emerging attack against deep neural network (DNN) implementations. Several prior works have utilized side-channel leakage to recover the model architecture while the target is executing on a hardware acceleration platform. In this work, we target an open-source deep-learning accelerator, Versatile Tensor Accelerator (VTA), and utilize electromagnetic (EM) side-channel leakage to comprehensively learn the association between DNN architecture configurations and EM emanations. We also consider the holistic system -- including the low-level tensor program code of the VTA accelerator on a Xilinx FPGA and explore the effect of such low-level configurations on the EM leakage. Our study demonstrates that both the optimization and configuration of tensor programs will affect the EM side-channel leakage. Gaining knowledge of the association between the low-level tensor program and the EM emanations, we propose NNReArch, a lightweight tensor program scheduling framework against side-channel-based DNN model architecture reverse engineering. Specifically, NNReArch targets reshaping the EM traces of different DNN operators, through scheduling the tensor program execution of the DNN model so as to confuse the adversary. NNReArch is a comprehensive protection framework supporting two modes, a balanced mode that strikes a balance between the DNN model confidentiality and execution performance, and a secure mode where the most secure setting is chosen. We implement and evaluate the proposed framework on the open-source VTA with state-of-the-art DNN architectures. The experimental results demonstrate that NNReArch can efficiently enhance the model architecture security with a small performance overhead. In addition, the proposed obfuscation technique makes reverse engineering of the DNN architecture significantly harder.

cs.CR↗

arXiv2021

Sensitive Samples Revisited: Detecting Neural Network Attacks Using Constraint Solvers

Neural Networks are used today in numerous security- and safety-relevant domains and are, as such, a popular target of attacks that subvert their classification capabilities, by manipulating the network parameters. Prior work has introduced sensitive samples -- inputs highly sensitive to parameter changes -- to detect such manipulations, and proposed a gradient ascent-based approach to compute them. In this paper we offer an alternative, using symbolic constraint solvers. We model the network and a formal specification of a sensitive sample in the language of the solver and ask for a solution. This approach supports a rich class of queries, corresponding, for instance, to the presence of certain types of attacks. Unlike earlier techniques, our approach does not depend on convex search domains, or on the suitability of a starting point for the search. We address the performance limitations of constraint solvers by partitioning the search space for the solver, and exploring the partitions according to a balanced schedule that still retains completeness of the search. We demonstrate the impact of the use of solvers in terms of functionality and search efficiency, using a case study for the detection of Trojan attacks on Neural Networks.

cs.LG↗