MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may reside in images, texts, or both. Existing model-level backdoor removal methods, largely designed for conventional classifiers, show limited effectiveness on MLLMs, while...
Jia-Li Wei, Ming Fan, Ming-Kun Zhang et al.· 0 citations
Program migration, which involves translating software systems from one programming language to another, is essential for modernizing legacy systems and improving maintainability. Recent large language models (LLMs) have demonstrated strong performance in code translation; however, existing methods and benchmarks still...
Xi-Tao Li, Xiao-Fei Xie, Jiang Wu et al.· Proceedings of the ACM on Pr...· 0 citations
GraphAHA is proposed, an adaptive graph search method with heterogeneous actions that organizes the test-time code generation in a typed directed acyclic graph and outperforms the strongest baseline for both models on both benchmarks by 4.1 percentage points on average.
Xi-Tao Li, Hai-Jun Wang, Ge-Ge Yuan et al.· 0 citations
Standardized token contracts (e.g., ERC-20) form the foundation of digital assets. However, attackers increasingly abuse this standardization to disguise malicious trap tokens. Unlike obvious violations, these contracts employ a strategy of"deceptive adherence": they strictly adhere to standard protocols to evade detec...
Yin Wu, Yi-Xuan Liu, Yi Li et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
