Fengwei Zhang

Pengzhou Cheng, Mu Han, Aoxue Li et al.

Intrusion detection is an important defensive measure for automotive communications security. Accurate frame detection models assist vehicles to avoid malicious attacks. Uncertainty and diversity regarding attack methods make this task challenging. However, the existing works have the limitation of only considering local features or the weak feature mapping of multi-features. To address these limitations, we present a novel model for automotive intrusion detection by spatial-temporal correlation features of in-vehicle communication traffic (STC-IDS). Specifically, the proposed model exploits an encoding-detection architecture. In the encoder part, spatial and temporal relations are encoded simultaneously. To strengthen the relationship between features, the attention-based convolutional network still captures spatial and channel features to increase the receptive field, while attention-LSTM builds meaningful relationships from previous time series or crucial bytes. The encoded information is then passed to detector for generating forceful spatial-temporal attention features and enabling anomaly classification. In particular, single-frame and multi-frame models are constructed to present different advantages respectively. Under automatic hyper-parameter selection based on Bayesian optimization, the model is trained to attain the best performance. Extensive empirical studies based on a real-world vehicle attack dataset demonstrate that STC-IDS has outperformed baseline methods and obtains fewer false-alarm rates while maintaining efficiency.

Liantao Song, Yiming Zhang, Fengwei Zhang et al.

The rapid advancement of cloud-native technologies has created an urgent need for security. Currently, confidential containers are increasingly deployed in multi-tenant environments. Existing confidential container designs mainly adopt a microVM-based architecture. Although this approach improves inter-container isolation, its complex software stack leads to high startup latency and significant resource overhead, making it unsuitable for short-lived container workloads. In this paper, we propose Fasco, a lightweight confidential container runtime based on the ARM Confidential Compute Architecture (CCA). Fasco directly instantiates each container as an independent Container Realm, leveraging CCA's hardware-enforced isolation to ensure the confidentiality and integrity of application data inside the container. In addition, Fasco introduces a dedicated System Realm to provide system services and resource management for container realms. Through exception forwarding and shared buffers, Fasco ensures isolation among different container realms. We have implemented a prototype of Fasco and evaluated its performance on ARMv8 hardware. Experimental results show that Fasco reduces the startup latency and performance overhead of existing confidential container architectures while maintaining a small TCB.

Pengzhou Cheng, Wei Du, Zongru Wu et al.

Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can transfer backdoors to various downstream tasks. In this paper, we introduce $\mathtt{maxEntropy}$, an entropy-based poisoning filter that mitigates such risks. To overcome the limitations of manual target setting and explicit triggers, we propose $\mathtt{SynGhost}$, an invisible and universal task-agnostic backdoor attack via syntactic transfer, further exposing vulnerabilities in pre-trained language models (PLMs). Specifically, $\mathtt{SynGhost}$ injects multiple syntactic backdoors into the pre-training space through corpus poisoning, while preserving the PLM's pre-training capabilities. Second, $\mathtt{SynGhost}$ adaptively selects optimal targets based on contrastive learning, creating a uniform distribution in the pre-training space. To identify syntactic differences, we also introduce an awareness module to minimize interference between backdoors. Experiments show that $\mathtt{SynGhost}$ poses significant threats and can transfer to various downstream tasks. Furthermore, $\mathtt{SynGhost}$ resists defenses based on perplexity, fine-pruning, and $\mathtt{maxEntropy}$. The code is available at https://github.com/Zhou-CyberSecurity-AI/SynGhost.

Zihao Li, Hongyi Lu, Yanan Guo et al.

GPU memory errors are a critical threat to deep learning (DL) frameworks, leading to crashes or even security issues. We introduce GPU-Fuzz, a fuzzer locating these issues efficiently by modeling operator parameters as formal constraints. GPU-Fuzz utilizes a constraint solver to generate test cases that systematically probe error-prone boundary conditions in GPU kernels. Applied to PyTorch, TensorFlow, and PaddlePaddle, we uncovered 13 unknown bugs, demonstrating the effectiveness of GPU-Fuzz in finding memory errors.

Hongyi Lu, Nian Liu, Shuai Wang et al.

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to regulate agent behavior through training or prompting, which does not offer fundamental security guarantees. We present ClawLess, a security framework that enforces formally verified policies on AI agents under a worst-case threat model where the agent itself may be adversarial. ClawLess formalizes a fine-grained security model over system entities, trust scopes, and permissions to express dynamic policies that adapt to agents' runtime behavior. These policies are translated into concrete security rules and enforced through a user-space kernel augmented with BPF-based syscall interception. This approach bridges the formal security model with practical enforcement, ensuring security regardless of the agent's internal design.

Jinghui Liao, Fengwei Zhang, Wenhai Sun et al.

State channel network is the most popular layer-2 solution to theissues of scalability, high transaction fees, and low transaction throughput of public Blockchain networks. However, the existing works have limitations that curb the wide adoption of the technology, such as the expensive creation and closure of channels, strict synchronization between the main chain and off-chain channels, frozen deposits, and inability to execute multi-party smart contracts. In this work, we present Speedster, an account-based state-channel system that aims to address the above issues. To this end, Speedster leverages the latest development of secure hardware to create dispute-free certified channels that can be operated efficiently off the Blockchain. Speedster is fully decentralized and provides better privacy protection. It supports fast native multi-party contract execution, which is missing in prior TEE-enabled channel networks. Compared to the Lightning Network, Speedster improves the throughput by about 10,000X and generates 97% less on-chain data with a comparable network scale.

Zhenyu Ning, Fengwei Zhang

The scale of Android applications in the market is growing rapidly. To efficiently detect the malicious behavior in these applications, an array of static analysis tools are proposed. However, static analysis tools suffer from code hiding techniques like packing, dynamic loading, self modifying, and reflection. In this paper, we thus present DexLego, a novel system that performs a reassembleable bytecode extraction for aiding static analysis tools to reveal the malicious behavior of Android applications. DexLego leverages just-in-time collection to extract data and bytecode from an application at runtime, and reassembles them to a new Dalvik Executable (DEX) file offline. The experiments on DroidBench and real-world applications show that DexLego correctly reconstructs the behavior of an application in the reassembled DEX file, and significantly improves analysis result of the existing static analysis systems.