Binary similarity analysis determines if two binary executables are from...
Large Language Models (LLMs) usually suffer from knowledge cutoff or fal...
Decompilation aims to recover the source code form of a binary executabl...
Recent advancements in deep learning have precipitated the emergence of ...
Self-supervised learning in computer vision trains on unlabeled data, su...
Recently decades have witnessed the empirical success of framing Knowled...
Deep Learning backdoor attacks have a threat model similar to traditiona...
We conduct a systematic study of backdoor vulnerabilities in normally tr...
High-quality traffic flow generation is the core module in building
simu...
Federated Learning (FL) is a distributed learning paradigm that enables
...
Pervasive backdoors are triggered by dynamic and pervasive input
perturb...
Transformers have achieved remarkable performance in widespread fields,
...
Pretrained language models can be effectively stimulated by textual prom...
In hyperspectral, high-quality spectral signals convey subtle spectral
d...
Self-supervised protein language models have proved their effectiveness ...
Despite the great success of Siamese-based trackers, their performance u...
Back-door attack poses a severe threat to deep learning systems. It inje...
Trojan (backdoor) attack is a form of adversarial attack on deep neural
...
We propose a new type of adversarial attack to Deep Neural Networks (DNN...