With the development of the wireless network techniques, the number of cyber-attack increases significantly, which has seriously threat the security of Wireless Local Area Network (WLAN). The traditional intrusion detection technology is a prevalent area of study for numerous years, but it may not have a good detection performance in a real-time way. Therefore, it is urgent to design a detection mechanism to detect the attacks timely. In this paper, we exploit a CDBN (Conditional Deep Belief Network)-based intrusion detection mechanism to recognize the attack features and perform the wireless network intrusion detection in real time. To avoid the impact of the imbalanced dataset and the data redundancy on the detection accuracy, a window-based instance selection algorithm “SamSelect” is adopted to undersample the majority class data samples, and a Stacked Contractive Auto-Encoder (SCAE) algorithm is proposed to reduce the dimension of the data samples. By doing so, our proposed mechanism can effectively detect the potential attack and achieve high accuracy. The experiment results show that CDBN can be effectively combined with “SamSelect” and SCAE, and the proposed mechanism has a high detection speed and accuracy, with the average detection time 1.14 ms and the detection accuracy 0.974.

Tao Sun, Linzheng Chai, Jian Yang, Yuwei Yin, Hongcheng Guo, Jiaheng Liu, Bing Wang, Liqun Yang, Zhoujun Li. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation. However, vanilla Transformer mainly exploits the top-layer representation, assuming the lower layers provide trivial or redundant information and thus ignoring the bottom-layer feature that is potentially valuable. In this work, we propose the G roup- Trans former model ( GTrans ) that flexibly divides multi-layer representations of both encoder and decoder into different groups and then fuses these group features to generate target words. To corroborate the effectiveness of the proposed method, extensive experiments and analytic experiments are conducted on three bilingual translation benchmarks and three multilingual translation tasks, including the IWLST-14, IWLST-17, LDC, WMT-14, WMT-21 and OPUS-100 benchmark. Experimental and analytical results demonstrate that our model outperforms its Transformer counterparts by a consistent gain. Furthermore, it can be successfully scaled up to 60 encoder layers and 36 decoder layers.

Fuzz testing is an dynamic program analysis technique designed for discovering vulnerabilities in IoT systems. The core goal is to deliberately feed maliciously crafted inputs into an IoT device or service, triggering vulnerabilities such as system crashes, buffer overflow exploits, and memory corruption, etc. Efficiently generating malicious inputs remains challenging, with leading methods often relying on randomly mutating existing valid inputs. In this work, we propose to adopt fine-tuned large language models (FuzzCoder) to learn patterns in the input files from successful attacks to guide future fuzzing explorations. Specifically, we develop a framework that leverages code large language models (LLMs) to guide the mutation process to perform meaningful input mutations. We formulate the mutation process as the sequence-to-sequence modeling, where LLM receives a sequence of bytes and outputs the mutated byte sequence. FuzzCoder is fine-tuned on our created instruction dataset (FuzzInstruct), where the successful fuzzing history is collected from the heuristic fuzzing tool. FuzzCoder can predict mutation positions and strategies for input files to trigger abnormal behaviors of the program. Most importantly, the experiment reveals results that FuzzCoder achieves better fuzzing performance compared to traditional and other American fuzzy lop (AFL)-based fuzzers, such as AFL, AFL++, AFLSmart, etc. On average, FuzzCoder achieves an improvement in code coverage of more than 20%, along with a significant increase in the number of crashes.