3 papers
cs.CR2026
Lilith: Backdoor Generalization under Training-Inference Trigger Shift
Zhou Feng, Jiahao Chen, Chunyi Zhou +6
Machine-learning services increasingly rely on public data, third-party providers, and outsourced training, creating opportunities for data-poisoning attacks that implant persisten…
cs.CR2026
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
Rui Yin, Tianxu Han, Naen Xu +8
Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can di…
cs.CL2026
"I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?
Naen Xu, Jiayi Sheng, Changjiang Li +7
Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground th…