Mingzhe Wang

Yuanliang Chen, Yu Jiang, Fuchen Ma et al.

Fuzzing is widely used for software vulnerability detection. There are various kinds of fuzzers with different fuzzing strategies, and most of them perform well on their targets. However, in industry practice and empirical study, the performance and generalization ability of those well-designed fuzzing strategies are challenged by the complexity and diversity of real-world applications. In this paper, inspired by the idea of ensemble learning, we first propose an ensemble fuzzing approach EnFuzz, that integrates multiple fuzzing strategies to obtain better performance and generalization ability than that of any constituent fuzzer alone. First, we define the diversity of the base fuzzers and choose those most recent and well-designed fuzzers as base fuzzers. Then, EnFuzz ensembles those base fuzzers with seed synchronization and result integration mechanisms. For evaluation, we implement EnFuzz , a prototype basing on four strong open-source fuzzers (AFL, AFLFast, AFLGo, FairFuzz), and test them on Google's fuzzing test suite, which consists of widely used real-world applications. The 24-hour experiment indicates that, with the same resources usage, these four base fuzzers perform variously on different applications, while EnFuzz shows better generalization ability and always outperforms others in terms of path coverage, branch coverage and crash discovery. Even compared with the best cases of AFL, AFLFast, AFLGo and FairFuzz, EnFuzz discovers 26.8%, 117%, 38.8% and 39.5% more unique crashes, executes 9.16%, 39.2%, 19.9% and 20.0% more paths and covers 5.96%, 12.0%, 21.4% and 11.1% more branches respectively.

Jingwen Zhou, Mingzhe Wang

Contrastive language-audio pretraining (CLAP) enables zero-shot audio classification, but standard inference classifies each clip in isolation and ignores the structure of the unlabeled test set. We present the first systematic study of TransCLIP-style transductive inference for CLAP: a text-anchored spherical Gaussian-mixture EM that refines zero-shot posteriors using the audio-embedding statistics of the test batch, with no labels, no gradients, and negligible compute (about 15 ms on one CPU core for 2,000 clips). Across ESC-50, UrbanSound8K, and VocalSound, this consistently improves top-1 accuracy by +4.6 to +9.2 points over the zero-shot baseline (e.g., 89.1 -> 94.8% on ESC-50, 73.8 -> 81.8% on UrbanSound8K). We further show that the gain (i) is governed by a simple operating boundary -- roughly 2.5 test samples per class per batch are required, with diminishing returns beyond ~5; (ii) is complementary to entropy-guided prompt weighting, with the combination reaching 96.2% on ESC-50; and (iii) attenuates but remains positive under long-tailed batches (+4.9 -> +3.1 points at a 20:1 imbalance), which we report as an explicit limitation. We also document a negative result: on TUT Urban Acoustic Scenes 2018, where zero-shot CLAP is near chance, transduction has no signal to amplify.

Mahmoud Azab, Mingzhe Wang, Max Smith et al.

We propose a new model for speaker naming in movies that leverages visual, textual, and acoustic modalities in an unified optimization framework. To evaluate the performance of our model, we introduce a new dataset consisting of six episodes of the Big Bang Theory TV show and eighteen full movies covering different genres. Our experiments show that our multimodal model significantly outperforms several competitive baselines on the average weighted F-score metric. To demonstrate the effectiveness of our framework, we design an end-to-end memory network model that leverages our speaker naming model and achieves state-of-the-art results on the subtitles task of the MovieQA 2017 Challenge.