Experimental results show that LTBD substantially outperforms inference-time defenses and performs competitively with training-based approaches, while preserving benign-task utility and introducing negligible inference overhead.
Lu-Man Zhao, Ming-Hui Xu, Yue Zhang et al.· 0 citations
Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has introduced a transformative paradigm driven by superior semantic reasoning and cross-e...
Zhengyang Shan, Xuan-Cheng Qian, Jia-Yu Xin et al.· Proceedings of the ACM on So...· 0 citations
Results show that proxy-based empirical gain achieves strong ranking agreement with proxy-defined realized utility and substantially outperforms row-count and token-count baselines in the tested setting, while the prototype provides a controlled sanity check of the valuation pipeline and its sensitivity to duplication-...
Ming-Hui Xu, Qi-Meng Luo, Kun Li et al.· arXiv.org· 1 citation
Multilingual and related-code evaluations further show effective forgetting with limited impact on useful programming capabilities, supporting UNBIND as a practical approach to selective code unlearning.
Zhengyang Shan, Jia-Yu Xin, Yan-Jun Lin et al.· 0 citations
OBLIVION, a controlled benchmark and defense harness for revoked-skill resurrection, and results support workflow-level evaluation beyond checking explicit skill entries support workflow-level evaluation beyond checking explicit skill entries.
Zhengyang Shan, Xuancheng Qian, Jiayu Xin et al.· 0 citations
Mask2Shield (M2S), a masked-forward alignment method that trains a model under this functional pruning procedure, reduces successful recomputed pruning attacks from 80--279 to 1--44 out of 313 prompts while generally preserving four capability benchmarks.