Existing studies of vulnerable pre-installed Android apps identify dangerous behavior by checking whether an app invokes an API from a predefined set of security-sensitive APIs. These sets usually exclude generic APIs to avoid false positives; unfortunately, this misses a class of vulnerabilities in which a generic API...
Hao-Tian Deng, Meng Hao, Han-Xiao Chen et al.· 0 citations
FragToken is proposed, a training-time framework that combines source-model self-distillation, capacity-aware filtering and budgeting, and BPE-Aligned Merging to induce fragmented generation under ordinary prompts while largely preserving model utility.
Zi-Han Wang, Rui Zhang, Xin-Yuan Qian et al.· 0 citations
CCCC, a covert communication scheme that is fully compliant with standard TLS 1.3, is proposed, the security properties of collision ciphertexts are formally defined, an efficient instantiation using AES-GCM and EdDSA is provided, and a full prototype is implemented.
Xin-Yue He, Yuan Zhang, Guo-Min Yang et al.· IEEE Transactions on Informa...· 0 citations
Expert parallelism (EP) is a common strategy for serving large Mixture-of-Experts (MoE) models across multiple GPUs by distributing experts among devices. Router decisions then determine both which experts process each token and which GPUs execute the resulting work. This procedure exposes a supply-chain attack surface...
Rui Zhang, Wenbo Jiang, Hong-Wei Li et al.· 1 citation
RAPID is proposed, a self-referenced latent maximization framework that removes external dependencies and encourages the same model update to induce consistently disruptive effects across training samples, thereby improving reachability and establishing a paradigm for real-time protection against unauthorized distillat...
Zi-Han Wang, Bo-Heng Li, Rui Zhang et al.· 0 citations
Retrieval-Augmented Generation (RAG) improves the factuality of large language models with external knowledge, yet conflicting evidence remains a fundamental challenge in dynamic and adversarial environments. Existing approaches often treat conflicts as static inconsistencies and select more reliable knowledge, overloo...
Xiao-Rui Nie, Hong-Wei Li, Shenghao Wu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.