Fuzzy Hashing as Perturbation-Consistent Adversarial Kernel Embedding
원문 초록
Measuring the similarity of two files is an important task in malware analysis, with fuzzy hash functions being a popular approach. Traditional fuzzy hash functions are data agnostic: they do not learn from a particular dataset how to determine similarity; their behavior is fixed across all datasets. In this paper, we demonstrate that fuzzy hash functions can be learned in a novel minimax training framework and that these learned fuzzy hash functions outperform traditional fuzzy hash functions at the file similarity task for Portable Executable files. In our approach, hash digests can be extracted from the kernel embeddings of two kernel networks, trained in a minimax framework, where the roles of players during training (i.e adversary versus generator) alternate along with the input data. We refer to this new minimax architecture as perturbation-consistent. The similarity score for a pair of files is the utility of the minimax game in equilibrium. Our experiments show that learned fuzzy hash functions generalize well, capable of determining that two files are similar even when one of those files was generated using insertion and deletion operations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers
DecompileBench: A Comprehensive Benchmark for Evaluating Decompilers in Real-World Scenarios
CyberLLMInstruct: A New Dataset for Analysing Safety of Fine-Tuned LLMs Using Cyber Security Data
Is Function Similarity Over-Engineered? Building a Benchmark
Magika: AI-Powered Content-Type Detection
Know Your Neighborhood: General and Zero-Shot Capable Binary Function Search Powered by Call Graphlets
토론
이 논문과 연결된 포럼 글이 아직 없습니다.