4 papers
Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders
Yiran Xiahou, Siliang Qin, Kai Chen +2
Diffusion-based image generation models produce high-quality images but may generate harmful or policy-violating content, motivating machine unlearning (MU) to selectively remove t…
PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent
Yuxin Cui, Zeyu Gao, Shuxian He +2
Decompilation is foundational to binary analysis, yet conventional tools prioritize human readability over strict recompilability and verifiable runtime correctness. While recent L…
Tady: A Neural Disassembler without Structural Constraint Violations
Siliang Qin, Fengrui Yang, Hao Wang +4
Disassembly is a crucial yet challenging step in binary analysis. While emerging neural disassemblers show promise for efficiency and accuracy, they frequently generate outputs vio…
DecompileBench: A Comprehensive Benchmark for Evaluating Decompilers in Real-World Scenarios
Zeyu Gao, Yuxin Cui, Hao Wang +4
Decompilers are fundamental tools for critical security tasks, from vulnerability discovery to malware analysis, yet their evaluation remains fragmented. Existing approaches primar…