KAI CHEN

We propose a novel backdoor injection approach in a "data-free" manner. We design a novel loss function for fine-tuning the original model into the backdoored one using the substitute data that is irrelevant to the main task, and optimize the fine-tuning to balance the backdoor injection and the performance on the main task. We conduct extensive experiments on various deep learning scenarios, and the evaluation results demonstrate that our data-free backdoor injection approach can efficiently embed backdoors with a nearly 100% attack success rate. [PDF] [CODE]... While emerging neural disassemblers show promise for efficiency and accuracy, they frequently generate outputs violating fundamental structural constraints, which significantly compromise their practical usability. We regularize the disassembly solution space by applying key structural constraints based on post-dominance relations. This approach systematically detects widespread errors in existing neural disassemblers'..

Primary location: Beijing China