Searcharxiv⌕ Search

arXiv subjects

Yuntao Liu

Publications and source records attributed to Yuntao Liu.

At least 19 recordsLinked to original sources

PolicySniff: Inferring Agent Policy States through Shared-GPU Execution

LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and operators keep these settings confidential by restricting access to prompts and responses. Audits check whether an agent obeys its setting, not whether a neighboring process can infer which setting is deployed. PolicySniff infers an agent's approval-policy state through shared-GPU execution. A co-resident attacker that knows the candidate settings and the task first profiles both settings, then times only its own GPU kernels while the agent processes the task. The policy prefix is cached before capture, so the attacker observes processing of a task suffix that is identical under both settings. On an eager sparse mixture-of-experts runtime, where each selected expert runs as separate work, a frozen and blinded study identified the deployed setting at 94.17% balanced accuracy on its primary estimand. Across all authorization conditions, accuracy was 88.82% on tasks for which both settings produce the same decision and 91.98% on tasks where they differ. Hardware replays of expert routing show that its temporal density and layer-and-bucket alignment carry the policy information. Behavioral compliance does not imply configuration confidentiality: deployments that keep their approval setting private should measure its distinguishability on the serving runtime and enforce authorization outside the model.

cs.CR↗

Privacy Leakage from Recurrent State in LLM Inference

Personalized LLM services place private facts and application instructions into a prompt, then retain representations of that context for later inference. Latent-state LLMs compress part of this history into fixed-size recurrent state. The information preserved by its learned updates is implicit, and later computation can expose it even when an observer receives neither the private text nor the responses. We investigate privacy leakage from recurrent state through partial-state probing and physical observation of its use. Our methodology separates recoverable information, persistence through public dialogue, causal influence on later decisions, and leakage through power. Experiments with released hybrid implementations show that a small state observation supports multiple predictions about private facts and response rules, and that personal attributes generalize to unseen authors. The information remains inferable after public dialogue and changes later decision margins. Complete-read power recovers private facts under a fixed execution schedule. On a partitioned GPU, an unprivileged account infers age from whole-device power during public requests; a separate state-isolation experiment establishes the recurrent contribution to this channel. These findings extend context confidentiality to the lifetime and execution of retained state. They identify access-control responsibilities for serving systems, telemetry restrictions for GPU operators, and data-dependent power leakage for accelerator designers.

cs.CR↗

Shielding design and construction for the XINGZHI cold neutron triple-axis spectrometer: integrating velocity selector, S-bender polarizer, and neutron guide

The optimized design and construction of shielding for the velocity selector, S-bender polarizer, and neutron guide in the XINGZHI cold neutron triple-axis spectrometer have been successfully completed. The challenge of limited space available for XINGZHI has been met by a compact shielding structure, developed through Monte Carlo simulations and realized by purpose-built mechanical design, thus leaving more floor space for the spectrometer. An innovative lead-antimony alloy ensures rigidity for self-support, while optimized tolerances for gaps between mating blocks meet safety, machinability, and mounting requirements. Additionally, a long-distance alignment method has been implemented, facilitating the alternating installation of the neutron guide and shielding system. After six years of operation, this structure has been verified to meet radiation safety standards while maximizing available space, marking a significant advancement in neutron instrumentation in China and offering valuable methodologies for future development.

physics.ins-det↗

QUFIG: GNN-Based Prediction of Quantum Fault Injection Vulnerabilities with Gate-Level Precision

The growing scale and accessibility of quantum hardware exposed new reliability and security challenges in the quantum computing workflow, such as the run-time fault injection attacks in cloud-based quantum computing platforms. However, existing works fail to identify vulnerabilities with gate-level precision or adapt to run-time environments. In this work, we formulate gate-level fault analysis as a learning-guided prioritization problem under restricted fidelity budgets. The framework uses a circuit-DAG-based GNN backbone to predict the vulnerability score of each gate to each type of injected fault, defined as the impact of the gate-fault pair on circuit fidelity. The gate-fault pairs are then ranked by their vulnerability score. Experiments on QASMbench and HamLib MaxCut show that QUFIG recovers high-impact vulnerable gate-fault pairs with fewer inspections than random and depth-based heuristics. Our results show that QUFIG can reduce the number of gates requiring inspection by 2.9--19.8% while maintaining effective fault identification, allowing quantum circuit designers to identify vulnerabilities and apply targeted defenses more efficiently.

quant-ph↗

Hardware-Rooted PUF Fingerprinting for Device-Level Traceability in Knowledge Distillation

Knowledge distillation (KD) enables model transfer across heterogeneous platforms and deployment environments, yet it exposes proprietary models to distillation-based theft, where an adversary extracts intellectual property (IP) by training a student model on teacher outputs. Current defenses, such as software watermarking or hardware-based access control, either fail to survive the distillation process or lack the granularity to identify the specific device responsible for a leak. Aiming to provide post-theft accountability and traceability, we propose a novel fingerprinting framework that superimposes device-specific Physical Unclonable Function (PUF) signatures onto teacher logits during distillation. By utilizing signatures derived from Ring Oscillator (RO) PUFs measured on a Xilinx Zynq-7020 FPGA, we ensure that any student model trained via KD inherits a unique, hardware-linked identity. Our framework is architecture-agnostic, enabling reliable identity inheritance across heterogeneous structures, including Convolutional Neural Networks, Vision Transformers, and encoders. To ensure robust attribution, we implement a two-stage recovery pipeline consisting of a neural decoder and Hamming-distance refinement, maintaining high detection accuracy even under noisy conditions. Furthermore, we introduce a multi-level logit encoding scheme to support large-scale device deployment. Experimental results demonstrate that the embedded fingerprints are resilient against common post-distillation modifications. These results establish a practical system-level approach for enabling hardware-linked model traceability in distributed AI deployment environments.

cs.CR↗

Agentic Router: An Execution-Grounded Continual Learning Approach With Memory

Large language model (LLM) agents provide a promising interface for command-line-based network operations, but a plausible command may still fail or introduce operational risk after execution. Existing approaches mainly focus on command generation or final configuration correctness, and do not use execution-grounded experience to jointly improve candidate coverage and action selection. We propose an execution-grounded dual-path consequence-aware agent for CLI-based SONiC operations, which generates multiple complete actions, predicts their execution consequences, and selects the final action through utility- and risk-aware reranking. The proposal-side path abstracts reusable operational lessons into retrievable guidance to improve feasible-action coverage without modifying the proposal LLM, while the selection-side path adapts the consequence predictor through session-level LoRA updates using real SSH feedback to improve conditional selection quality. Experiments over multi-turn SONiC operation sessions with different Qwen3 proposal models show that the framework improves feasible-action coverage and top-1 execution success, and that the two adaptation paths provide complementary gains over interaction.

cs.AI↗

CLOAQ: Combined Logic and Angle Obfuscation for Quantum Circuits

In the realm of quantum computing, quantum circuits serve as essential depictions of quantum algorithms, which are then compiled into executable operations for quantum computations. Quantum compilers are responsible for converting these algorithmic quantum circuits into versions compatible with specific quantum hardware, thus connecting quantum software with hardware. Nevertheless, untrusted quantum compilers present notable threats. They have the potential to result in the theft of quantum circuit designs and jeopardize sensitive intellectual property (IP). In this work, we propose CLOAQ, a quantum circuit obfuscation (QCO) approach that hides the logic and the phase angles of selected gates within the obfuscated quantum circuit. To evaluate the effectiveness of CLOAQ, we sample the input state uniformly from the Hilbert space of all qubits, which is more accurate than prior work that use all-|0> inputs. Our results show that CLOAQ benefits from the synergy between logic and phase protections. Compared with prior QCO approaches using only one perspective, the combined method is more resilient to attacks and causes greater functional disruption when the unlocking key is incorrect.

cs.CR↗

PDF: PUF-based DNN Fingerprinting for Knowledge Distillation Traceability

Knowledge distillation transfers large teacher models to compact student models, enabling deployment on resource-limited platforms while suffering minimal performance degradation. However, this paradigm could lead to various security risks, especially model theft. Existing defenses against model theft, such as watermarking and secure enclaves, focus primarily on identity authentication and incur significant resource costs. Aiming to provide post-theft accountability and traceability, we propose a novel fingerprinting framework that superimposes device-specific Physical Unclonable Function (PUF) signatures onto teacher logits during distillation. Compared with watermarking or secure enclaves, our approach is lightweight, requires no architectural changes, and enables traceability of any leaked or cloned model. Since the signatures are based on PUFs, this framework is robust against reverse engineering and tampering attacks. In this framework, the signature recovery process consists of two stages: first a neural network-based decoder and then a Hamming distance decoder. Furthermore, we also propose a bit compression scheme to support a large number of devices. Experiment results demonstrate that our framework achieves high key recovery rate and negligible accuracy loss while allowing a tunable trade-off between these two key metrics. These results show that the proposed framework is a practical and robust solution for protecting distilled models.

cs.CR↗

Security Evaluation of Quantum Circuit Split Compilation under an Oracle-Guided Attack

Quantum circuits are the fundamental representation of quantum algorithms and constitute valuable intellectual property (IP). Multiple quantum circuit obfuscation (QCO) techniques have been proposed in prior research to protect quantum circuit IP against malicious compilers. However, there has not been a thorough security evaluation of these schemes. In this work, we investigate the resilience of split compilation against an oracle-guided attack. Split compilation is one of the most studied QCO techniques, where the circuit to be compiled is split into two disjoint partitions. Each split circuit is known to the compiler, but the interconnections between them are hidden. We propose an oracle-guided security evaluation framework in which candidate connections are systematically tested against input-output observations, with iteratively pruned inconsistent mappings. This hierarchical matching process exploits the reversibility of quantum gates and reduces the search space compared to brute-force enumeration. Experimental evaluation in the RevLib benchmark suite shows that only a small number of I/O pairs are sufficient to recover the correct inter-split connections and reconstruct the entire circuits. Our study marks the first thorough security evaluations in quantum IP protection and highlights the necessity of such evaluations in the development of new protection schemes.

quant-ph↗

TroLL: Exploiting Structural Similarities between Logic Locking and Hardware Trojans

Logic locking and hardware Trojans are two fields in hardware security that have been mostly developed independently from each other. In this paper, we identify the relationship between these two fields. We find that a common structure that exists in many logic locking techniques has desirable properties of hardware Trojans (HWT). We then construct a novel type of HWT, called Trojans based on Logic Locking (TroLL), in a way that can evade state-of-the-art ATPG-based HWT detection techniques. In an effort to detect TroLL, we propose customization of existing state-of-the-art ATPG-based HWT detection approaches as well as adapting the SAT-based attacks on logic locking to HWT detection. In our experiments, we use random sampling as reference. It is shown that the customized ATPG-based approaches are the best performing but only offer limited improvement over random sampling. Moreover, their efficacy also diminishes as TroLL's triggers become longer (i.e. have more bits specified). We thereby highlight the need to find a scalable HWT detection approach for TroLL.

cs.CR↗

Red Teaming Methodology for Design Obfuscation

The main goal of design obfuscation schemes is to protect sensitive design details from untrusted parties in the VLSI supply chain, including but not limited to off-shore foundries and untrusted end users. In this work, we provide a systematic red teaming approach to evaluate the security of design obfuscation approaches. Specifically, we propose security metrics and evaluation methodology for the scenarios where the adversary does not have access to a working chip. A case study on the RIPPER tool developed by the University of Florida indicates that more information is leaked about the structure of the original design than commonly considered.

cs.CR↗

TetrisLock: Quantum Circuit Split Compilation with Interlocking Patterns

In quantum computing, quantum circuits are fundamental representations of quantum algorithms, which are compiled into executable functions for quantum solutions. Quantum compilers transform algorithmic quantum circuits into one compatible with target quantum computers, bridging quantum software and hardware. However, untrusted quantum compilers pose significant risks. They can lead to the theft of quantum circuit designs and compromise sensitive intellectual property (IP). In this paper, we propose TetrisLock, a split compilation method for quantum circuit obfuscation that uses an interlocking splitting pattern to effectively protect IP with minimal resource overhead. Our approach divides the quantum circuit into two interdependent segments, ensuring that reconstructing the original circuit functionality is possible only by combining both segments and eliminating redundancies. This method makes reverse engineering by an untrusted compiler unrealizable, as the original circuit is never fully shared with any single entity. Also, our approach eliminates the need for a trusted compiler to process the inserted random circuit, thereby relaxing the security requirements. Additionally, it defends against colluding attackers with mismatched numbers of qubits, while maintaining low overhead by preserving the original depth of the quantum circuit. We demonstrate our method by using established RevLib benchmarks, showing that it achieves a minimal impact on functional accuracy (less than 1%) while significantly reducing the likelihood of IP inference.

quant-ph↗

OPAQUE: Obfuscating Phase in Quantum Circuit Compilation for Efficient IP Protection

Quantum compilers play a crucial role in quantum computing by converting these algorithmic quantum circuits into forms compatible with specific quantum computer hardware. However, untrusted quantum compilers present considerable risks, including the potential theft of quantum circuit intellectual property (IP) and compromise of the functionality (e.g. Trojan insertion). Quantum circuit obfuscation techniques protect quantum IP by transforming a quantum circuit into a key-dependent version before compilation and restoring the compiled circuit's functionality with the correct key. This prevents the untrusted compiler from knowing the circuit's original functionality. Existing quantum circuit obfuscation techniques focus on inserting key qubits to control key gates. One added key gate can represent at most one Boolean key bit. In this paper, we propose OPAQUE, a phase-based quantum circuit obfuscation approach where we use the angle of rotation gates as the secret keys. The rotation angle is a continuous value, which makes it possible to represent multiple key bits. Moreover, phase gates are usually implemented as virtual gates in quantum hardware, diminishing their cost and impact on accuracy.

quant-ph↗

E-LoQ: Enhanced Locking for Quantum Circuit IP Protection

In recent years, quantum computing has started to demonstrate superior efficiency to classical computing. In quantum computing, quantum circuits that implement specific quantum algorithms are usually not directly executable on quantum computer hardware. Quantum circuit compilers decompose high-level quantum gates into the hardware's native gates and optimize the circuits for accuracy and performance. However, untrusted quantum compilers risk stealing original quantum designs (quantum circuits), leading to the theft of sensitive intellectual property (IP). In classical computing, logic locking is a family of techniques to secure integrated circuit (ICs) designs against reverse engineering and IP piracy. This technique involves inserting a keyed value into the circuit, ensuring the correct output is achieved only with the correct key. To address similar issues in quantum circuit protection, we propose an enhanced locking technique for quantum circuits (E-LoQ) where multiple key bits can be condensed into one key qubit. Compared to previous work that used one qubit for each key bit, our approach achieves higher security levels. We have demonstrated the practicality of our method through experiments on a set of benchmark quantum circuits. The effectiveness of E-LoQ was measured by assessing the divergence distance from the original circuit. Our results demonstrate that E-LoQ effectively conceals the function of the original quantum circuit, with an average fidelity degradation of less than 1%.

quant-ph↗

Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception

Collaborative perception by leveraging the shared semantic information plays a crucial role in overcoming the individual limitations of isolated agents. However, existing collaborative perception methods tend to focus solely on the spatial features of semantic information, while neglecting the importance of the temporal dimension. Consequently, the potential benefits of collaboration remain underutilized. In this article, we propose Select2Col, a novel collaborative perception framework that takes into account the \underline{s}patial-t\underline{e}mpora\underline{l} importanc\underline{e} of semanti\underline{c} informa\underline{t}ion. Within the Select2Col, we develop a collaborator selection method that utilizes a lightweight graph neural network (GNN) to estimate the importance of semantic information (IoSI) of each collaborator in enhancing perception performance, thereby identifying contributive collaborators while excluding those that potentially bring negative impact. Moreover, we present a semantic information fusion algorithm called HPHA (historical prior hybrid attention), which integrates multi-scale attention and short-term attention modules to capture the IoSI in feature representation from the spatial and temporal dimensions respectively, and assigns IoSI-consistent weights for efficient fusion of information from selected collaborators. Extensive experiments on three open datasets demonstrate that our proposed Select2Col significantly improves the perception performance compared to state-of-the-art approaches. The code associated with this research is publicly available at https://github.com/huangqzj/Select2Col/.

cs.CV↗

DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking

The functionality of a deep learning (DL) model can be stolen via model extraction where an attacker obtains a surrogate model by utilizing the responses from a prediction API of the original model. In this work, we propose a novel watermarking technique called DynaMarks to protect the intellectual property (IP) of DL models against such model extraction attacks in a black-box setting. Unlike existing approaches, DynaMarks does not alter the training process of the original model but rather embeds watermark into a surrogate model by dynamically changing the output responses from the original model prediction API based on certain secret parameters at inference runtime. The experimental outcomes on Fashion MNIST, CIFAR-10, and ImageNet datasets demonstrate the efficacy of DynaMarks scheme to watermark surrogate models while preserving the accuracies of the original models deployed in edge devices. In addition, we also perform experiments to evaluate the robustness of DynaMarks against various watermark removal strategies, thus allowing a DL model owner to reliably prove model ownership.

cs.CR↗

Robust and Attack Resilient Logic Locking with a High Application-Level Impact

Logic locking is a hardware security technique to intellectual property (IP) against security threats in the IC supply chain, especially untrusted fabs. Such techniques incorporate additional locking circuitry within an IC that induces incorrect functionality when an incorrect key is provided. The amount of error induced is known as the effectiveness of the locking technique. "SAT attacks" provide a strong mathematical formulation to find the correct key of locked circuits. In order to achieve high SAT resilience(i.e. complexity of SAT attacks), many conventional logic locking schemes fail to inject sufficient error into the circuit. For example, in the case of SARLock and Anti-SAT, there are usually very few (or only one) input minterms that cause any error at the circuit output. The state-of-the-art stripped functionality logic locking (SFLL) technique introduced a trade-off between SAT resilience and effectiveness. In this work, we prove that such a trade-off is universal in logic locking. In order to attain high effectiveness of locking without compromising SAT resilience, we propose a novel logic locking scheme, called Strong Anti-SAT (SAS). In addition to SAT attacks, removal-based attacks are also popular against logic locking. Based on SAS, we propose Robust SAS (RSAS) which is resilient to removal attacks and maintains the same SAT resilience and as effectiveness as SAS. SAS and RSAS have the following significant improvements over existing techniques. (1) SAT resilience of SAS and RSAS against SAT attack is not compromised by increase in effectiveness. (2) In contrast to prior work focusing solely on the circuit-level locking impact, we integrate SAS-locked modules into a processor and show that SAS has a high application-level impact. (3) Our experiments show that SAS and RSAS exhibit better SAT resilience than SFLL and have similar effectiveness.

cs.CR↗

Visual Confusion Label Tree For Image Classification

Convolution neural network models are widely used in image classification tasks. However, the running time of such models is so long that it is not the conforming to the strict real-time requirement of mobile devices. In order to optimize models and meet the requirement mentioned above, we propose a method that replaces the fully-connected layers of convolution neural network models with a tree classifier. Specifically, we construct a Visual Confusion Label Tree based on the output of the convolution neural network models, and use a multi-kernel SVM plus classifier with hierarchical constraints to train the tree classifier. Focusing on those confusion subsets instead of the entire set of categories makes the tree classifier more discriminative and the replacement of the fully-connected layers reduces the original running time. Experiments show that our tree classifier obtains a significant improvement over the state-of-the-art tree classifier by 4.3% and 2.4% in terms of top-1 accuracy on CIFAR-100 and ImageNet datasets respectively. Additionally, our method achieves 124x and 115x speedup ratio compared with fully-connected layers on AlexNet and VGG16 without accuracy decline.

cs.CV↗